http://www.jmlr.org
JMLRJournal of Machine Learning Research
Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra
http://jmlr.org/papers/v21/20-933.html
2020Vardan Papyan
Numerous researchers recently applied empirical spectral analysis to the study of modern deep learning classifiers. We identify and discuss an important formal class/cross-class structure and show how it lies at the origin of the many visually striking features observed in deep neural network spectra, some of which were reported in recent articles, others are unveiled here for the first time. These include spectral outliers, “spikes”, and small but distinct continuous distributions, “bumps”, often seen beyond the edge of a “main bulk”.
Online matrix factorization for Markovian data and applications to Network Dictionary Learning
http://jmlr.org/papers/v21/20-444.html
2020Hanbaek Lyu, Deanna Needell, Laura Balzano
Online Matrix Factorization (OMF) is a fundamental tool for dictionary learning problems, giving an approximate representation of complex data sets in terms of a reduced number of extracted features. Convergence guarantees for most of the OMF algorithms in the literature assume independence between data matrices, and the case of dependent data streams remains largely unexplored. In this paper, we show that a non-convex generalization of the well-known OMF algorithm for i.i.d. stream of data in Mairal et al. converges almost surely to the set of critical points of the expected loss function, even when the data matrices are functions of some underlying Markov chain satisfying a mild mixing condition. This allows one to extract features more efficiently from dependent data streams, as there is no need to subsample the data sequence to approximately satisfy the independence assumption. As the main application, by combining online non-negative matrix factorization and a recent MCMC algorithm for sampling motifs from networks, we propose a novel framework of Network Dictionary Learning, which extracts “network dictionary patches” from a given network in an online manner that encodes main features of the network. We demonstrate this technique and its application to network denoising problems on real-world network data.
High-dimensional quantile tensor regression
http://jmlr.org/papers/v21/20-383.html
2020Wenqi Lu, Zhongyi Zhu, Heng Lian
Quantile regression is an indispensable tool for statistical learning. Traditional quantile regression methods consider vector-valued covariates and estimate the corresponding coefficient vector. Many modern applications involve data with a tensor structure. In this paper, we propose a quantile regression model which takes tensors as covariates, and present an estimation approach based on Tucker decomposition. It effectively reduces the number of parameters, leading to efficient estimation and feasible computation. We also use a sparse Tucker decomposition, which is a popular approach in the literature, to further reduce the number of parameters when the dimension of the tensor is large. We propose an alternating update algorithm combined with alternating direction method of multipliers (ADMM). The asymptotic properties of the estimators are established under suitable conditions. The numerical performances are demonstrated via simulations and an application to a crowd density estimation problem.
Learning Mixed Latent Tree Models
http://jmlr.org/papers/v21/20-365.html
2020Can Zhou, Xiaofei Wang, Jianhua Guo
Latent structural learning has attracted more attention in recent years. But most related works only focuses on pure continuous or pure discrete data. In this paper, we consider mixed latent tree models for mixed data mining. We address the latent structural learning and parameter estimation for those mixed models. For structural learning, we propose a consistent bottom-up algorithm, and give a finite sample bound guarantee for the exact structural recovery. For parameter estimation, we suggest a moment estimator by exploiting matrix decomposition, and prove asymptotic normality of the estimator. Experiments on the simulated and real data support that our method is valid for mining the hierarchical structure and latent information.
Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning
http://jmlr.org/papers/v21/20-312.html
2020Peter Henderson, Jieru Hu, Joshua Romoff, Emma Brunskill, Dan Jurafsky, Joelle Pineau
Accurate reporting of energy and carbon usage is essential for understanding the potential climate impacts of machine learning research. We introduce a framework that makes this easier by providing a simple interface for tracking realtime energy consumption and carbon emissions, as well as generating standardized online appendices. Utilizing this framework, we create a leaderboard for energy efficient reinforcement learning algorithms to incentivize responsible research in this area as an example for other areas of machine learning. Finally, based on case studies using our framework, we propose strategies for mitigation of carbon emissions and reduction of energy consumption. By making accounting easier, we hope to further the sustainable development of machine learning experiments and spur more research into energy efficient algorithms.
Adaptive Rates for Total Variation Image Denoising
http://jmlr.org/papers/v21/20-301.html
2020Francesco Ortelli, Sara van de Geer
We study the theoretical properties of image denoising via total variation penalized least-squares. We define the total vatiation in terms of the two-dimensional total discrete derivative of the image and show that it gives rise to denoised images that are piecewise constant on rectangular sets. We prove that, if the true image is piecewise constant on just a few rectangular sets, the denoised image converges to the true image at a parametric rate, up to a log factor. More generally, we show that the denoised image enjoys oracle properties, that is, it is almost as good as if some aspects of the true image were known. In other words, image denoising with total variation regularization leads to an adaptive reconstruction of the true image.
On Efficient Adjustment in Causal Graphs
http://jmlr.org/papers/v21/20-175.html
2020Janine Witte, Leonard Henckel, Marloes H. Maathuis, Vanessa Didelez
We consider estimation of a total causal effect from observational data via covariate adjustment. Ideally, adjustment sets are selected based on a given causal graph, reflecting knowledge of the underlying causal structure. Valid adjustment sets are, however, not unique. Recent research has introduced a graphical criterion for an 'optimal' valid adjustment set (O-set). For a given graph, adjustment by the O-set yields the smallest asymptotic variance compared to other adjustment sets in certain parametric and non-parametric models. In this paper, we provide three new results on the O-set. First, we give a novel, more intuitive graphical characterisation: We show that the O-set is the parent set of the outcome node(s) in a suitable latent projection graph, which we call the forbidden projection. An important property is that the forbidden projection preserves all information relevant to total causal effect estimation via covariate adjustment, making it a useful methodological tool in its own right. Second, we extend the existing IDA algorithm to use the O-set, and argue that the algorithm remains semi-local. This is implemented in the R-package pcalg. Third, we present assumptions under which the O-set can be viewed as the target set of popular non-graphical variable selection algorithms such as stepwise backward selection.
A Group-Theoretic Framework for Data Augmentation
http://jmlr.org/papers/v21/20-163.html
2020Shuxiao Chen, Edgar Dobriban, Jane H. Lee
Data augmentation is a widely used trick when training deep neural networks: in addition to the original data, properly transformed data are also added to the training set. However, to the best of our knowledge, a clear mathematical framework to explain the performance benefits of data augmentation is not available. In this paper, we develop such a theoretical framework. We show data augmentation is equivalent to an averaging operation over the orbits of a certain group that keeps the data distribution approximately invariant. We prove that it leads to variance reduction. We study empirical risk minimization, and the examples of exponential families, linear regression, and certain two-layer neural networks. We also discuss how data augmentation could be used in problems with symmetry where other approaches are prevalent, such as in cryo-electron microscopy (cryo-EM).
Rank-based Lasso - efficient methods for high-dimensional robust model selection
http://jmlr.org/papers/v21/20-120.html
2020Wojciech Rejchel, Małgorzata Bogdan
We consider the problem of identifying significant predictors in large data bases, where the response variable depends on the linear combination of explanatory variables through an unknown monotonic link function, corrupted with the noise from the unknown distribution. We utilize the natural, robust and efficient approach, which relies on replacing values of the response variables by their ranks and then identifying significant predictors by using well known Lasso. We provide new consistency results for the proposed procedure (called ,,RankLasso”) and extend the scope of its applications by proposing its thresholded and adaptive versions. Our theoretical results show that these modifications can identify the set of relevant predictors under a wide range of data generating scenarios. Theoretical results are supported by the simulation study and the real data analysis, which show that our methods can properly identify relevant predictors, even when the error terms come from the Cauchy distribution and the link function is nonlinear. They also demonstrate the superiority of the modified versions of RankLasso over its regular version in the case when predictors are substantially correlated. The numerical study shows also that RankLasso performs substantially better in model selection than LADLasso, which is a well established methodology for robust model selection.
Best Practices for Scientific Research on Neural Architecture Search
http://jmlr.org/papers/v21/20-056.html
2020Marius Lindauer, Frank Hutter
Finding a well-performing architecture is often tedious for both deep learning practitioners and researchers, leading to tremendous interest in the automation of this task by means of neural architecture search (NAS). Although the community has made major strides in developing better NAS methods, the quality of scientific empirical evaluations in the young field of NAS is still lacking behind that of other areas of machine learning. To address this issue, we describe a set of possible issues and ways to avoid them, leading to the NAS best practices checklist available at http://automl.org/nas_checklist.pdf.
Fair Data Adaptation with Quantile Preservation
http://jmlr.org/papers/v21/19-966.html
2020Drago Plečko, Nicolai Meinshausen
Fairness of classification and regression has received much attention recently and various, partially non-compatible, criteria have been proposed. The fairness criteria can be enforced for a given classifier or, alternatively, the data can be adapted to ensure that every classifier trained on the data will adhere to desired fairness criteria. We present a practical data adaption method based on quantile preservation in causal structural equation models. The data adaptation is based on a presumed counterfactual model for the data. While the counterfactual model itself cannot be verified experimentally, we show that certain population notions of fairness are still guaranteed even if the counterfactual model is misspecified. The nature of the fulfilled observational non-causal fairness notion (such as demographic parity, separation or sufficiency) depends on the structure of the underlying causal model and the choice of resolving variables. We describe an implementation of the proposed data adaptation procedure based on Random Forests and demonstrate its practical use on simulated and real-world data.
Efficient Inference for Nonparametric Hawkes Processes Using Auxiliary Latent Variables
http://jmlr.org/papers/v21/19-930.html
2020Feng Zhou, Zhidong Li, Xuhui Fan, Yang Wang, Arcot Sowmya, Fang Chen
The expressive ability of classic Hawkes processes is limited due to the parametric assumption on the baseline intensity and triggering kernel. Therefore, it is desirable to perform inference in a data-driven, nonparametric approach. Many recent works have proposed nonparametric Hawkes process models based on Gaussian processes (GP). However, the likelihood is non-conjugate to the prior resulting in a complicated and time-consuming inference procedure. To address the problem, we present the sigmoid Gaussian Hawkes process model in this paper: the baseline intensity and triggering kernel are both modeled as the sigmoid transformation of random trajectories drawn from a GP. By introducing auxiliary latent random variables (branching structure, P\'{o}lya-Gamma random variables and latent marked Poisson processes), the likelihood is converted to two decoupled components with a Gaussian form which allows for an efficient conjugate analytical inference. Using the augmented likelihood, we derive an efficient Gibbs sampling algorithm to sample from the posterior; an efficient expectation-maximization (EM) algorithm to obtain the maximum a posteriori (MAP) estimate and furthermore an efficient mean-field variational inference algorithm to approximate the posterior. To further accelerate the inference, a sparse GP approximation is introduced to reduce complexity. We demonstrate the performance of our three algorithms on both simulated and real data. The experiments show that our proposed inference algorithms can recover well the underlying prompting characteristics efficiently.
Risk Bounds for Reservoir Computing
http://jmlr.org/papers/v21/19-902.html
2020Lukas Gonon, Lyudmila Grigoryeva, Juan-Pablo Ortega
We analyze the practices of reservoir computing in the framework of statistical learning theory. In particular, we derive finite sample upper bounds for the generalization error committed by specific families of reservoir computing systems when processing discrete-time inputs under various hypotheses on their dependence structure. Non-asymptotic bounds are explicitly written down in terms of the multivariate Rademacher complexities of the reservoir systems and the weak dependence structure of the signals that are being handled. This allows, in particular, to determine the minimal number of observations needed in order to guarantee a prescribed estimation accuracy with high probability for a given reservoir family. At the same time, the asymptotic behavior of the devised bounds guarantees the consistency of the empirical risk minimization procedure for various hypothesis classes of reservoir functionals.
Minimal Learning Machine: Theoretical Results and Clustering-Based Reference Point Selection
http://jmlr.org/papers/v21/19-786.html
2020Joonas Hämäläinen, Alisson S. C. Alencar, Tommi Kärkkäinen, César L. C. Mattos, Amauri H. Souza Júnior, João P. P. Gomes
The Minimal Learning Machine (MLM) is a nonlinear, supervised approach based on learning linear mapping between distance matrices computed in input and output data spaces, where distances are calculated using a subset of points called reference points. Its simple formulation has attracted several recent works on extensions and applications. In this paper, we aim to address some open questions related to the MLM. First, we detail the theoretical aspects that assure the MLM's interpolation and universal approximation capabilities, which had previously only been empirically verified. Second, we identify the major importance of the task of selecting reference points for the MLM's generalization capability. Several clustering-based methods for reference point selection in regression scenarios are then proposed and analyzed. Based on an extensive empirical evaluation, we conclude that the evaluated methods are both scalable and useful. Specifically, for a small number of reference points, the clustering-based methods outperform the standard random selection of the original MLM formulation.
algcomparison: Comparing the Performance of Graphical Structure Learning Algorithms with TETRAD
http://jmlr.org/papers/v21/19-773.html
2020Joseph D. Ramsey, Daniel Malinsky, Kevin V. Bui
In this report we describe a tool for comparing the performance of graphical causal structure learning algorithms implemented in the TETRAD freeware suite of causal analysis methods. Currently the tool is available as package in the TETRAD source code (written in Java). Simulations can be done varying the number of runs, sample sizes, and data modalities. Performance on this simulated data can then be compared for a number of algorithms, with parameters varied and with performance statistics as selected, producing a publishable report. The package presented here may also be used to compare structure learning methods across platforms and programming languages, i.e., to compare algorithms implemented in TETRAD with those implemented in MATLAB, Python, or R.
The Error-Feedback framework: SGD with Delayed Gradients
http://jmlr.org/papers/v21/19-748.html
2020Sebastian U. Stich, Sai Praneeth Karimireddy
We analyze (stochastic) gradient descent (SGD) with delayed updates on smooth quasi-convex and non-convex functions and derive concise, non-asymptotic, convergence rates. We show that the rate of convergence in all cases consists of two terms: (i) a stochastic term which is not affected by the delay, and (ii) a higher order deterministic term which is only linearly slowed down by the delay. Thus, in the presence of noise, the effects of the delay become negligible after a few iterations and the algorithm converges at the same optimal rate as standard SGD. This result extends a line of research that showed similar results in the asymptotic regime or for strongly-convex quadratic functions only. We further show similar results for SGD with more intricate form of delayed gradients---compressed gradients under error compensation and for local~SGD where multiple workers perform local steps before communicating with each other. In all of these settings, we improve upon the best known rates. These results show that SGD is robust to compressed and/or delayed stochastic gradient updates. This is in particular important for distributed parallel implementations, where asynchronous and communication efficient methods are the key to achieve linear speedups for optimization with multiple devices.
Lower Bounds for Learning Distributions under Communication Constraints via Fisher Information
http://jmlr.org/papers/v21/19-737.html
2020Leighton Pate Barnes, Yanjun Han, Ayfer Ozgur
We consider the problem of learning high-dimensional, nonparametric and structured (e.g., Gaussian) distributions in distributed networks, where each node in the network observes an independent sample from the underlying distribution and can use $k$ bits to communicate its sample to a central processor. We consider three different models for communication. Under the independent model, each node communicates its sample to a central processor by independently encoding it into $k$ bits. Under the more general sequential or blackboard communication models, nodes can share information interactively but each node is restricted to write at most $k$ bits on the final transcript. We characterize the impact of the communication constraint $k$ on the minimax risk of estimating the underlying distribution under $\ell^2$ loss. We develop minimax lower bounds that apply in a unified way to many common statistical models and reveal that the impact of the communication constraint can be qualitatively different depending on the tail behavior of the score function associated with each model. A key ingredient in our proofs is a geometric characterization of Fisher information from quantized samples.
Convex Programming for Estimation in Nonlinear Recurrent Models
http://jmlr.org/papers/v21/19-723.html
2020Sohail Bahmani, Justin Romberg
We propose a formulation for nonlinear recurrent models that includes simple parametric models of recurrent neural networks as a special case. The proposed formulation leads to a natural estimator in the form of a convex program. We provide a sample complexity for this estimator in the case of stable dynamics, where the nonlinear recursion has a certain contraction property, and under certain regularity conditions on the input distribution. We evaluate the performance of the estimator by simulation on synthetic data. These numerical experiments also suggest the extent at which the imposed theoretical assumptions may be relaxed.
Dual Extrapolation for Sparse GLMs
http://jmlr.org/papers/v21/19-587.html
2020Mathurin Massias, Samuel Vaiter, Alexandre Gramfort, Joseph Salmon
Generalized Linear Models (GLM) form a wide class of regression and classification models, where prediction is a function of a linear combination of the input variables. For statistical inference in high dimension, sparsity inducing regularizations have proven to be useful while offering statistical guarantees. However, solving the resulting optimization problems can be challenging: even for popular iterative algorithms such as coordinate descent, one needs to loop over a large number of variables. To mitigate this, techniques known as screening rules and working sets diminish the size of the optimization problem at hand, either by progressively removing variables, or by solving a growing sequence of smaller problems. For both techniques, significant variables are identified thanks to convex duality arguments. In this paper, we show that the dual iterates of a GLM exhibit a Vector AutoRegressive (VAR) behavior after sign identification, when the primal problem is solved with proximal gradient descent or cyclic coordinate descent. Exploiting this regularity, one can construct dual points that offer tighter certificates of optimality, enhancing the performance of screening rules and working set algorithms.
Robust high dimensional learning for Lipschitz and convex losses
http://jmlr.org/papers/v21/19-585.html
2020Chinot Geoffrey, Lecué Guillaume, Lerasle Matthieu
We establish risk bounds for Regularized Empirical Risk Minimizers (RERM) when the loss is Lipschitz and convex and the regularization function is a norm. In a first part, we obtain these results in the i.i.d. setup under subgaussian assumptions on the design. In a second part, a more general framework where the design might have heavier tails and data may be corrupted by outliers both in the design and the response variables is considered. In this situation, RERM performs poorly in general. We analyse an alternative procedure based on median-of-means principles and called “minmax MOM”. We show optimal subgaussian deviation rates for these estimators in the relaxed setting. The main results are meta-theorems allowing a wide-range of applications to various problems in learning theory. To show a non-exhaustive sample of these potential applications, it is applied to classification problems with logistic loss functions regularized by LASSO and SLOPE, to regression problems with Huber loss regularized by Group LASSO and Total Variation. Another advantage of the minmax MOM formulation is that it suggests a systematic way to slightly modify descent based algorithms used in high-dimensional statistics to make them robust to outliers. We illustrate this principle in a Simulations section where a “ minmax MOM” version of classical proximal descent algorithms are turned into robust to outliers algorithms.
Spectral Deconfounding via Perturbed Sparse Linear Models
http://jmlr.org/papers/v21/19-545.html
2020Domagoj Ćevid, Peter Bühlmann, Nicolai Meinshausen
Standard high-dimensional regression methods assume that the underlying coefficient vector is sparse. This might not be true in some cases, in particular in presence of hidden, confounding variables. Such hidden confounding can be represented as a high-dimensional linear model where the sparse coefficient vector is perturbed. For this model, we develop and investigate a class of methods that are based on running the Lasso on preprocessed data. The preprocessing step consists of applying certain spectral transformations that change the singular values of the design matrix. We show that, under some assumptions, one can achieve the usual Lasso $\ell_1$-error rate for estimating the underlying sparse coefficient vector, despite the presence of confounding. Our theory also covers the Lava estimator (Chernozhukov et al., 2017) for a special model class. The performance of the methodology is illustrated on simulated data and a genomic dataset.
Fast Exact Matrix Completion: A Unified Optimization Framework for Matrix Completion
http://jmlr.org/papers/v21/19-471.html
2020Dimitris Bertsimas, Michael Lingzhi Li
We formulate the problem of matrix completion with and without side information as a non-convex optimization problem. We design fastImpute based on non-convex gradient descent and show it converges to a global minimum that is guaranteed to recover closely the underlying matrix while it scales to matrices of sizes beyond $10^5 \times 10^5$. We report experiments on both synthetic and real-world datasets that show fastImpute is competitive in both the accuracy of the matrix recovered and the time needed across all cases. Furthermore, when a high number of entries are missing, fastImpute is over $75\%$ lower in MAPE and $15$ times faster than current state-of-the-art matrix completion methods in both the case with side information and without.
Stable Regression: On the Power of Optimization over Randomization
http://jmlr.org/papers/v21/19-408.html
2020Dimitris Bertsimas, Ivan Paskov
We investigate and ultimately suggest remediation to the widely held belief that the best way to train regression models is via random assignment of our data to training and validation sets. In particular, we show that taking a robust optimization approach, and optimally selecting such training and validation sets, leads to models that not only perform significantly better than their randomly constructed counterparts in terms of prediction error, but more importantly, are considerably more stable in the sense that the standard deviation of the resulting predictions, as well as of the model coefficients, is greatly reduced. Moreover, we show that this optimization approach to training is far more effective at recovering the true support of a given data set, i.e., correctly identifying important features while simultaneously excluding spurious ones. We further compare the robust optimization approach to cross validation and find that optimization continues to have a performance edge albeit smaller. Finally, we show that this optimization approach to training is equivalent to building models that are robust to all subpopulations in the data, and thus in particular are robust to the hardest subpopulation, which leads to interesting domain specific interpretations through the use of optimal classification trees. The proposed robust optimization algorithm is efficient and scales training to essentially any desired size.
Nonparametric graphical model for counts
http://jmlr.org/papers/v21/19-362.html
2020Arkaprava Roy, David B Dunson
Although multivariate count data are routinely collected in many application areas, there is surprisingly little work developing flexible models for characterizing their dependence structure. This is particularly true when interest focuses on inferring the conditional independence graph. In this article, we propose a new class of pairwise Markov random field-type models for the joint distribution of a multivariate count vector. By employing a novel type of transformation, we avoid restricting to non-negative dependence structures or inducing other restrictions through truncations. Taking a Bayesian approach to inference, we choose a Dirichlet process prior for the distribution of a random effect to induce great flexibility in the specification. An efficient Markov chain Monte Carlo (MCMC) algorithm is developed for posterior computation. We prove various theoretical properties, including posterior consistency, and show that our COunt Nonparametric Graphical Analysis (CONGA) approach has good performance relative to competitors in simulation studies. The methods are motivated by an application to neuron spike count data in mice.
Posterior sampling strategies based on discretized stochastic differential equations for machine learning applications
http://jmlr.org/papers/v21/19-339.html
2020Frederik Heber, Žofia Trst’anová, Benedict Leimkuhler
With the advent of GPU-assisted hardware and maturing high-efficiency software platforms such as TensorFlow and PyTorch, Bayesian posterior sampling for neural networks becomes plausible. In this article we discuss Bayesian parametrization in machine learning based on Markov Chain Monte Carlo methods, specifically discretized stochastic differential equations such as Langevin dynamics and extended system methods in which an ensemble of walkers is employed to enhance sampling. We provide a glimpse of the potential of the sampling-intensive approach by studying (and visualizing) the loss landscape of a neural network applied to the MNIST data set. Moreover, we investigate how the sampling efficiency itself can be significantly enhanced through an ensemble quasi-Newton preconditioning method. This article accompanies the release of a new TensorFlow software package, the Thermodynamic Analytics ToolkIt, which is used in the computational experiments.
Significance Tests for Neural Networks
http://jmlr.org/papers/v21/19-264.html
2020Enguerrand Horel, Kay Giesecke
We develop a pivotal test to assess the statistical significance of the feature variables in a single-layer feed-forward neural network regression model. We propose a gradient-based test statistic and study its asymptotics using non-parametric techniques. Under technical conditions, the limiting distribution is given by a mixture of chi-square distributions. The tests enable one to discern the impact of individual variables on the prediction of a neural network. The test statistic can be used to rank variables according to their influence. Simulation results illustrate the computational efficiency and the performance of the test. An empirical application to house price valuation highlights the behavior of the test using actual data.
A Sparse Semismooth Newton Based Proximal Majorization-Minimization Algorithm for Nonconvex Square-Root-Loss Regression Problems
http://jmlr.org/papers/v21/19-247.html
2020Peipei Tang, Chengjing Wang, Defeng Sun, Kim-Chuan Toh
In this paper, we consider high-dimensional nonconvex square-root-loss regression problems and introduce a proximal majorization-minimization (PMM) algorithm for solving these problems. Our key idea for making the proposed PMM to be efficient is to develop a sparse semismooth Newton method to solve the corresponding subproblems. By using the Kurdyka- Lojasiewicz property exhibited in the underlining problems, we prove that the PMM algorithm converges to a d-stationary point. We also analyze the oracle property of the initial subproblem used in our algorithm. Extensive numerical experiments are presented to demonstrate the high efficiency of the proposed PMM algorithm.
Recovery of a Mixture of Gaussians by Sum-of-Norms Clustering
http://jmlr.org/papers/v21/19-218.html
2020Tao Jiang, Stephen Vavasis, Chen Wen Zhai
Sum-of-norms clustering is a method for assigning $n$ points in $\mathbf{R}^d$ to $K$ clusters, $1\le K\le n$, using convex optimization. Recently, Panahi (2017) proved that sum-of-norms clustering is guaranteed to recover a mixture of Gaussians under the restriction that the number of samples is not too large. The purpose of this note is to lift this restriction, that is, show that sum-of-norms clustering can recover a mixture of Gaussians even as the number of samples tends to infinity. Our proof relies on an interesting characterization of clusters computed by sum-of-norms clustering that was developed inside a proof of the agglomeration conjecture by Chiquet et al. (2017). Because we believe this theorem has independent interest, we restate and reprove the Chiquet et al. (2017) result herein.
Ultra-High Dimensional Single-Index Quantile Regression
http://jmlr.org/papers/v21/19-173.html
2020Yuankun Zhang, Heng Lian, Yan Yu
We consider a flexible semiparametric single-index quantile regression model where the number of covariates may be ultra-high dimensional, and the number of the relevant covariates is potentially diverging. The approach is particularly appealing to uncover the complex heterogeneity in high-dimensional data, incorporate nonlinearity and potential interaction, avoid the curse of dimensionality, and allow different variables to be included at different quantile levels. We estimate the unknown function via polynomial splines nonparametrically and adopt a nonconvex penalty function to identify the sparse variable set. We further extend it to partially linear single-index quantile model where both the single-index components in the nonparametric term and the partially linear components can be in ultra-high dimension. However, a number of major challenges arise in developing both theory and computation: (a) The model is highly nonlinear in single-index coefficients because the high-dimensional single-index covariates are embedded inside the unknown flexible function. (b) The data are ultra-high dimensional where the dimension of the single-index covariates ($p_n$) is diverging or even in the exponential order of sample size $n$. (c) The objective function is non-smooth for quantile regression. (d) Nonconvex variable selection such as SCAD is adopted for regularization. (e) The extended partially linear single-index quantile models may include both ultra-high dimensional ($p_n$) single-index covariates and ultra-high dimensional ($q_n$) partially linear covariates. We develop a novel approach using empirical process techniques in establishing the theoretical properties of the nonconvex penalized estimators for partially linear single-index quantile models and show those estimators indeed possess the oracle property in ultra-high dimensional setting. We propose an efficient algorithm to circumvent the computational challenges. The results of Monte Carlo simulations and an application to gene expression data demonstrate the effectiveness of the proposed models and estimation method.
Geomstats: A Python Package for Riemannian Geometry in Machine Learning
http://jmlr.org/papers/v21/19-027.html
2020Nina Miolane, Nicolas Guigui, Alice Le Brigant, Johan Mathe, Benjamin Hou, Yann Thanwerdas, Stefan Heyder, Olivier Peltre, Niklas Koep, Hadi Zaatiti, Hatem Hajri, Yann Cabanes, Thomas Gerald, Paul Chauchat, Christian Shewmake, Daniel Brooks, Bernhard Kainz, Claire Donnat, Susan Holmes, Xavier Pennec
We introduce Geomstats, an open-source Python package for computations and statistics on nonlinear manifolds such as hyperbolic spaces, spaces of symmetric positive definite matrices, Lie groups of transformations, and many more. We provide object-oriented and extensively unit-tested implementations. Manifolds come equipped with families of Riemannian metrics with associated exponential and logarithmic maps, geodesics, and parallel transport. Statistics and learning algorithms provide methods for estimation, clustering, and dimension reduction on manifolds. All associated operations are vectorized for batch computation and provide support for different execution backends---namely NumPy, PyTorch, and TensorFlow. This paper presents the package, compares it with related libraries, and provides relevant code examples. We show that Geomstats provides reliable building blocks to both foster research in differential geometry and statistics and democratize the use of Riemannian geometry in machine learning applications. The source code is freely available under the MIT license at geomstats.ai.
Theory of Curriculum Learning, with Convex Loss Functions
http://jmlr.org/papers/v21/18-751.html
2020Daphna Weinshall, Dan Amir
Curriculum Learning is motivated by human cognition, where teaching often involves gradually exposing the learner to examples in a meaningful order, from easy to hard. Although methods based on this concept have been empirically shown to improve performance of several machine learning algorithms, no theoretical analysis has been provided even for simple cases. To address this shortfall, we start by formulating an ideal definition of difficulty score - the loss of the optimal hypothesis at a given datapoint. We analyze the possible contribution of curriculum learning based on this score in two convex problems - linear regression, and binary classification by hinge loss minimization. We show that in both cases, the convergence rate of SGD optimization decreases monotonically with the difficulty score, in accordance with earlier empirical results. We also prove that when the difficulty score is fixed, the convergence rate of SGD optimization is monotonically increasing with respect to the loss of the current hypothesis at each point. We discuss how these results settle some confusion in the literature where two apparently opposing heuristics are reported to improve performance: curriculum learning in which easier points are given priority, vs hard data mining where the more difficult points are sought out.
Learning Sums of Independent Random Variables with Sparse Collective Support
http://jmlr.org/papers/v21/18-531.html
2020Anindya De, Philip M. Long, Rocco A. Servedio
We study the learnability of sums of independent integer random variables given a bound on the size of the union of their supports. For $\mathcal{A} \subset \mathbb{Z}_{+}$, a {sum of independent random variables with collective support $\mathcal{A}$} (called an $\mathcal{A}$-sum in this paper) is a distribution $\mathbf{S} = \mathbf{X}_1 + \cdots + \mathbf{X}_N$ where the $\mathbf{X}_i$'s are mutually independent (but not necessarily identically distributed) integer random variables with $\cup_i \mathrm{supp}(\mathbf{X}_i) \subseteq \mathcal{A}.$ We give two main algorithmic results for learning such distributions. First, for the case $| \mathcal{A} | = 3$, we give an algorithm for learning an unknown $\mathcal{A}$-sum to accuracy $\epsilon$ using $\mathrm{poly}(1/\epsilon)$ samples and running in time $\mathrm{poly}(1/\epsilon)$, independent of $N$ and of the elements of $\mathcal{A}$. Second, for an arbitrary constant $k \geq 4$, if $\mathcal{A} = \{ a_1,...,a_k\}$ with $0 \leq a_1 < ... < a_k$, we give an algorithm that uses $\mathrm{poly}(1/\epsilon) \cdot \log \log a_k$ samples (independent of $N$) and runs in time $\mathrm{poly}(1/\epsilon, \log a_k).$ We prove an essentially matching lower bound: if $|\mathcal{A}| = 4$, then any algorithm must use \[ \Omega(\log \log a_4) \] samples even for learning to constant accuracy. We also give similar-in-spirit (but quantitatively very different) algorithmic results, and essentially matching lower bounds, for the case in which $\mathcal{A}$ is not known to the learner. Our algorithms and lower bounds together settle the question of how the sample complexity of learning sums of independent integer random variables scales with the elements in the union of their supports, both in the known-support and unknown-support settings. Finally, all our algorithms easily extend to the “semi-agnostic” learning model, in which training data is generated from a distribution that is only $c \epsilon$-close to some $\mathcal{A}$-sum for a constant $c>0$.
Diffeomorphic Learning
http://jmlr.org/papers/v21/18-415.html
2020Laurent Younes
We introduce in this paper a learning paradigm in which training data is transformed by a diffeomorphic transformation before prediction. The learning algorithm minimizes a cost function evaluating the prediction error on the training set penalized by the distance between the diffeomorphism and the identity. The approach borrows ideas from shape analysis where diffeomorphisms are estimated for shape and image alignment, and brings them in a previously unexplored setting, estimating, in particular diffeomorphisms in much larger dimensions. After introducing the concept and describing a learning algorithm, we present diverse applications, mostly with synthetic examples, demonstrating the potential of the approach, as well as some insight on how it can be improved.
AdaGrad stepsizes: Sharp convergence over nonconvex landscapes
http://jmlr.org/papers/v21/18-352.html
2020Rachel Ward, Xiaoxia Wu, Leon Bottou
Adaptive gradient methods such as AdaGrad and its variants update the stepsize in stochastic gradient descent on the fly according to the gradients received along the way; such methods have gained widespread use in large-scale optimization for their ability to converge robustly, without the need to fine-tune the stepsize schedule. Yet, the theoretical guarantees to date for AdaGrad are for online and convex optimization. We bridge this gap by providing theoretical guarantees for the convergence of AdaGrad for smooth, nonconvex functions. We show that the norm version of AdaGrad (AdaGrad-Norm) converges to a stationary point at the $\mathcal{O}(\log(N)/\sqrt{N})$ rate in the stochastic setting, and at the optimal $\mathcal{O}(1/N)$ rate in the batch (non-stochastic) setting -- in this sense, our convergence guarantees are “sharp”. In particular, the convergence of AdaGrad-Norm is robust to the choice of all hyper-parameters of the algorithm, in contrast to stochastic gradient descent whose convergence depends crucially on tuning the step-size to the (generally unknown) Lipschitz smoothness constant and level of stochastic noise on the gradient. Extensive numerical experiments are provided to corroborate our theoretical findings; moreover, the experiments suggest that the robustness of AdaGrad-Norm extends to the models in deep learning.
Spectral bandits
http://jmlr.org/papers/v21/16-529.html
2020Tomáš Kocák, Rémi Munos, Branislav Kveton, Shipra Agrawal, Michal Valko
Smooth functions on graphs have wide applications in manifold and semi-supervised learning. In this work, we study a bandit problem where the payoffs of arms are smooth on a graph. This framework is suitable for solving online learning problems that involve graphs, such as content-based recommendation. In this problem, each item we can recommend is a node of an undirected graph and its expected rating is similar to the one of its neighbors. The goal is to recommend items that have high expected ratings. We aim for the algorithms where the cumulative regret with respect to the optimal policy would not scale poorly with the number of nodes. In particular, we introduce the notion of an effective dimension, which is small in real-world graphs, and propose three algorithms for solving our problem that scale linearly and sublinearly in this dimension. Our experiments on content recommendation problem show that a good estimator of user preferences for thousands of items can be learned from just tens of node evaluations.
On the Theoretical Guarantees for Parameter Estimation of Gaussian Random Field Models: A Sparse Precision Matrix Approach
http://jmlr.org/papers/v21/14-241.html
2020Sam Davanloo Tajbakhsh, Necdet Serhat Aybat, Enrique Del Castillo
Iterative methods for fitting a Gaussian Random Field (GRF) model via maximum likelihood (ML) estimation requires solving a nonconvex optimization problem. The problem is aggravated for anisotropic GRFs where the number of covariance function parameters increases with the dimension. Even evaluation of the likelihood function requires $O(n^3)$ floating point operations, where $n$ denotes the number of data locations. In this paper, we propose a new two-stage procedure to estimate the parameters of second-order stationary GRFs. First, a convex likelihood problem regularized with a weighted $\ell_1$-norm, utilizing the available distance information between observation locations, is solved to fit a sparse precision (inverse covariance) matrix to the observed data. Second, the parameters of the covariance function are estimated by solving a least squares problem. Theoretical error bounds for the solutions of stage I and II problems are provided, and their tightness are investigated.
Dynamic Assortment Optimization with Changing Contextual Information
http://jmlr.org/papers/v21/19-1054.html
2020Xi Chen, Yining Wang, Yuan Zhou
In this paper, we study the dynamic assortment optimization problem over a finite selling season of length $T$. At each time period, the seller offers an arriving customer an assortment of substitutable products under a cardinality constraint, and the customer makes the purchase among offered products according to a discrete choice model. Most existing work associates each product with a real-valued fixed mean utility and assumes a multinomial logit choice (MNL) model. In many practical applications, feature/contextual information of products is readily available. In this paper, we incorporate the feature information by assuming a linear relationship between the mean utility and the feature. In addition, we allow the feature information of products to change over time so that the underlying choice model can also be non-stationary. To solve the dynamic assortment optimization under this changing contextual MNL model, we need to simultaneously learn the underlying unknown coefficient and make the decision on the assortment. To this end, we develop an upper confidence bound (UCB) based policy and establish the regret bound on the order of $\tilde{O}(d\sqrt{T})$, where $d$ is the dimension of the feature and $\tilde{O}$ suppresses logarithmic dependence. We further establish a lower bound $\Omega(d\sqrt{T}/{K})$, where $K$ is the cardinality constraint of an offered assortment, which is usually small. When $K$ is a constant, our policy is optimal up to logarithmic factors. In the exploitation phase of the UCB algorithm, we need to solve a combinatorial optimization problem for assortment optimization based on the learned information. We further develop an approximation algorithm and an efficient greedy heuristic. The effectiveness of the proposed policy is further demonstrated by our numerical studies.
Mining Topological Structure in Graphs through Forest Representations
http://jmlr.org/papers/v21/19-1032.html
2020Robin Vandaele, Yvan Saeys, Tijl De Bie
We consider the problem of inferring simplified topological substructures—which we term backbones—in metric and non-metric graphs. Intuitively, these are subgraphs with ‘few’ nodes, multifurcations, and cycles, that model the topology of the original graph well. We present a multistep procedure for inferring these backbones. First, we encode local (geometric) information of each vertex in the original graph by means of the boundary coefficient (BC) to identify ‘core’ nodes in the graph. Next, we construct a forest representation of the graph, termed an f-pine, that connects every node of the graph to a local ‘core’ node. The final backbone is then inferred from the f-pine through CLOF (Constrained Leaves Optimal subForest), a novel graph optimization problem we introduce in this paper. On a theoretical level, we show that CLOF is NP-hard for general graphs. However, we prove that CLOF can be efficiently solved for forest graphs, a surprising fact given that CLOF induces a nontrivial monotone submodular set function maximization problem on tree graphs. This result is the basis of our method for mining backbones in graphs through forest representation. We qualitatively and quantitatively confirm the applicability, effectiveness, and scalability of our method for discovering backbones in a variety of graph-structured data, such as social networks, earthquake locations scattered across the Earth, and high-dimensional cell trajectory data.
Provable Convex Co-clustering of Tensors
http://jmlr.org/papers/v21/18-155.html
2020Eric C. Chi, Brian J. Gaines, Will Wei Sun, Hua Zhou, Jian Yang
Cluster analysis is a fundamental tool for pattern discovery of complex heterogeneous data. Prevalent clustering methods mainly focus on vector or matrix-variate data and are not applicable to general-order tensors, which arise frequently in modern scientific and business applications. Moreover, there is a gap between statistical guarantees and computational efficiency for existing tensor clustering solutions due to the nature of their non-convex formulations. In this work, we bridge this gap by developing a provable convex formulation of tensor co-clustering. Our convex co-clustering (CoCo) estimator enjoys stability guarantees and its computational and storage costs are polynomial in the size of the data. We further establish a non-asymptotic error bound for the CoCo estimator, which reveals a surprising “blessing of dimensionality” phenomenon that does not exist in vector or matrix-variate cluster analysis. Our theoretical findings are supported by extensive simulated studies. Finally, we apply the CoCo estimator to the cluster analysis of advertisement click tensor data from a major online company. Our clustering results provide meaningful business insights to improve advertising effectiveness.
Multiclass Anomaly Detector: the CS++ Support Vector Machine
http://jmlr.org/papers/v21/16-122.html
2020Alistair Shilton, Sutharshan Rajasegarar, Marimuthu Palaniswami
A new support vector machine (SVM) variant, called CS++-SVM, is presented combining multiclass classification and anomaly detection in a single-step process to create a trained machine that can simultaneously classify test data belonging to classes represented in the training set and label as anomalous test data belonging to classes not represented in the training set. A theoretical analysis of the properties of the new method, showing how it combines properties inherited both from the conic-segmentation SVM (CS-SVM) and the $1$-class SVM (to which the method described reduces to in the case of unlabelled training data), is given. Finally, experimental results are presented to demonstrate the effectiveness of the algorithm for both simulated and real-world data.
scikit-survival: A Library for Time-to-Event Analysis Built on Top of scikit-learn
http://jmlr.org/papers/v21/20-729.html
2020Sebastian Pölsterl
scikit-survival is an open-source Python package for time-to-event analysis fully compatible with scikit-learn. It provides implementations of many popular machine learning techniques for time-to-event analysis, including penalized Cox model, Random Survival Forest, and Survival Support Vector Machine. In addition, the library includes tools to evaluate model performance on censored time-to-event data. The documentation contains installation instructions, interactive notebooks, and a full description of the API. scikit-survival is distributed under the GPL-3 license with the source code and detailed instructions available at https://github.com/sebp/scikit-survival
Random Smoothing Might be Unable to Certify $\ell_\infty$ Robustness for High-Dimensional Images
http://jmlr.org/papers/v21/20-209.html
2020Avrim Blum, Travis Dick, Naren Manoj, Hongyang Zhang
We show a hardness result for random smoothing to achieve certified adversarial robustness against attacks in the $\ell_p$ ball of radius $\epsilon$ when $p>2$. Although random smoothing has been well understood for the $\ell_2$ case using the Gaussian distribution, much remains unknown concerning the existence of a noise distribution that works for the case of $p>2$. This has been posed as an open problem by Cohen et al. (2019) and includes many significant paradigms such as the $\ell_\infty$ threat model. In this work, we show that any noise distribution $\mathcal{D}$ over $\mathbb{R}^d$ that provides $\ell_p$ robustness for all base classifiers with $p>2$ must satisfy $\mathbb{E} \eta_i^2=\Omega(d^{1-2/p}\epsilon^2(1-\delta)/\delta^2)$ for 99% of the features (pixels) of vector $\eta\sim\mathcal{D}$, where $\epsilon$ is the robust radius and $\delta$ is the score gap between the highest-scored class and the runner-up. Therefore, for high-dimensional images with pixel values bounded in $[0,255]$, the required noise will eventually dominate the useful information in the images, leading to trivial smoothed classifiers.
ProtoAttend: Attention-Based Prototypical Learning
http://jmlr.org/papers/v21/20-042.html
2020Sercan O. Arik, Tomas Pfister
We propose a novel inherently interpretable machine learning method that bases decisions on few relevant examples that we call prototypes. Our method, ProtoAttend, can be integrated into a wide range of neural network architectures including pre-trained models. It utilizes an attention mechanism that relates the encoded representations to samples in order to determine prototypes. Protoattend yields superior results in three high impact problems without sacrificing accuracy of the original model: (1)it enables high-quality interpretability that outputs samples most relevant to the decision-making (i.e. a sample-based interpretability method); (2) it achieves state of the art confidence estimation by quantifying the mismatch across prototype labels; and (3) it obtains state of the art in distribution mismatch detection. All these can be achieved with minimal additional test time and a practically viable training time computational cost.
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation
http://jmlr.org/papers/v21/19-976.html
2020Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Raetsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem
The idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we provide a sober look at recent progress in the field and challenge some common assumptions. We first theoretically show that the unsupervised learning of disentangled representations is fundamentally impossible without inductive biases on both the models and the data. Then, we train over $14000$ models covering most prominent methods and evaluation metrics in a reproducible large-scale experimental study on eight data sets. We observe that while the different methods successfully enforce properties “encouraged” by the corresponding losses, well-disentangled models seemingly cannot be identified without supervision. Furthermore, different evaluation metrics do not always agree on what should be considered “disentangled” and exhibit systematic differences in the estimation. Finally, increased disentanglement does not seem to necessarily lead to a decreased sample complexity of learning for downstream tasks. Our results suggest that future work on disentanglement learning should be explicit about the role of inductive biases and (implicit) supervision, investigate concrete benefits of enforcing disentanglement of the learned representations, and consider a reproducible experimental setup covering several data sets.
Learning Data-adaptive Non-parametric Kernels
http://jmlr.org/papers/v21/19-900.html
2020Fanghui Liu, Xiaolin Huang, Chen Gong, Jie Yang, Li Li
In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.
Functional Martingale Residual Process for High-Dimensional Cox Regression with Model Averaging
http://jmlr.org/papers/v21/19-829.html
2020Baihua He, Yanyan Liu, Yuanshan Wu, Guosheng Yin, Xingqiu Zhao
Regularization methods for the Cox proportional hazards regression with high-dimensional survival data have been studied extensively in the literature. However, if the model is misspecified, this would result in misleading statistical inference and prediction. To enhance the prediction accuracy for the relative risk and the survival probability, we propose three model averaging approaches for the high-dimensional Cox proportional hazards regression. Based on the martingale residual process, we define the delete-one cross-validation (CV) process, and further propose three novel CV functionals, including the end-time CV, integrated CV, and supremum CV, to achieve more accurate prediction for the risk quantities of clinical interest. The optimal weights for candidate models, without the constraint of summing up to one, can be obtained by minimizing these functionals, respectively. The proposed model averaging approach can attain the lowest possible prediction loss asymptotically. Furthermore, we develop a greedy model averaging algorithm to overcome the computational obstacle when the dimension is high. The performances of the proposed model averaging procedures are evaluated via extensive simulation studies, demonstrating that our methods achieve superior prediction accuracy over the existing regularization methods. As an illustration, we apply the proposed methods to the mantle cell lymphoma study.
On Convergence of Distributed Approximate Newton Methods: Globalization, Sharper Bounds and Beyond
http://jmlr.org/papers/v21/19-764.html
2020Xiao-Tong Yuan, Ping Li
The DANE algorithm is an approximate Newton method popularly used for communication-efficient distributed machine learning. Reasons for the interest in DANE include scalability and efficiency. Convergence of DANE, however, can be tricky; its appealing convergence rate is only rigorous for quadratic objective function, and for more general convex functions the known results are no stronger than those of the classic first-order methods. To remedy these drawbacks, we propose in this article some new alternatives of DANE which are more suitable for analysis. We first introduce a simple variant of DANE equipped with backtracking line search, for which global asymptotic convergence and sharper local non-asymptotic convergence guarantees can be proved for both quadratic and non-quadratic strongly convex functions. Then we propose a heavy-ball method to accelerate the convergence of DANE, showing that the near-tight local rate of convergence can be established for strongly convex functions, and with proper modification of the algorithm about the same result applies globally to linear prediction models. Numerical evidence is provided to confirm the theoretical and practical advantages of our methods.
Sobolev Norm Learning Rates for Regularized Least-Squares Algorithms
http://jmlr.org/papers/v21/19-734.html
2020Simon Fischer, Ingo Steinwart
Learning rates for least-squares regression are typically expressed in terms of $L_2$-norms. In this paper we extend these rates to norms stronger than the $L_2$-norm without requiring the regression function to be contained in the hypothesis space. In the special case of Sobolev reproducing kernel Hilbert spaces used as hypotheses spaces, these stronger norms coincide with fractional Sobolev norms between the used Sobolev space and $L_2$. As a consequence, not only the target function but also some of its derivatives can be estimated without changing the algorithm. From a technical point of view, we combine the well-known integral operator techniques with an embedding property, which so far has only been used in combination with empirical process arguments. This combination results in new finite sample bounds with respect to the stronger norms. From these finite sample bounds our rates easily follow. Finally, we prove the asymptotic optimality of our results in many cases.
Two-Stage Approach to Multivariate Linear Regression with Sparsely Mismatched Data
http://jmlr.org/papers/v21/19-645.html
2020Martin Slawski, Emanuel Ben-David, Ping Li
A tacit assumption in linear regression is that (response, predictor)-pairs correspond to identical observational units. A series of recent works have studied scenarios in which this assumption is violated under terms such as “Unlabeled Sensing and “Regression with Unknown Permutation”. In this paper, we study the setup of multiple response variables and a notion of mismatches that generalizes permutations in order to allow for missing matches as well as for one-to-many matches. A two-stage method is proposed under the assumption that most pairs are correctly matched. In the first stage, the regression parameter is estimated by handling mismatches as contaminations, and subsequently the generalized permutation is estimated by a basic variant of matching. The approach is both computationally convenient and equipped with favorable statistical guarantees. Specifically, it is shown that the conditions for permutation recovery become considerably less stringent as the number of responses $m$ per observation increase. Particularly, for $m = \Omega(\log n)$, the required signal-to-noise ratio no longer depends on the sample size $n$. Numerical results on synthetic and real data are presented to support the main findings of our analysis.
Dynamic Control of Stochastic Evolution: A Deep Reinforcement Learning Approach to Adaptively Targeting Emergent Drug Resistance
http://jmlr.org/papers/v21/19-546.html
2020Dalit Engelhardt
The challenge in controlling stochastic systems in which low-probability events can set the system on catastrophic trajectories is to develop a robust ability to respond to such events without significantly compromising the optimality of the baseline control policy. This paper presents CelluDose, a stochastic simulation-trained deep reinforcement learning adaptive feedback control prototype for automated precision drug dosing targeting stochastic and heterogeneous cell proliferation. Drug resistance can emerge from random and variable mutations in targeted cell populations; in the absence of an appropriate dosing policy, emergent resistant subpopulations can proliferate and lead to treatment failure. Dynamic feedback dosage control holds promise in combatting this phenomenon, but the application of traditional control approaches to such systems is fraught with challenges due to the complexity of cell dynamics, uncertainty in model parameters, and the need in medical applications for a robust controller that can be trusted to properly handle unexpected outcomes. Here, training on a sample biological scenario identified single-drug and combination therapy policies that exhibit a $100\%$ success rate at suppressing cell proliferation and responding to diverse system perturbations while establishing low-dose no-event baselines. These policies were found to be highly robust to variations in a key model parameter subject to significant uncertainty and unpredictable dynamical changes.
A Numerical Measure of the Instability of Mapper-Type Algorithms
http://jmlr.org/papers/v21/19-540.html
2020Francisco Belchi, Jacek Brodzki, Matthew Burfitt, Mahesan Niranjan
Mapper is an unsupervised machine learning algorithm generalising the notion of clustering to obtain a geometric description of a dataset. The procedure splits the data into possibly overlapping bins which are then clustered. The output of the algorithm is a graph where nodes represent clusters and edges represent the sharing of data points between two clusters. However, several parameters must be selected before applying Mapper and the resulting graph may vary dramatically with the choice of parameters. We define an intrinsic notion of Mapper instability that measures the variability of the output as a function of the choice of parameters required to construct a Mapper output. Our results and discussion are general and apply to all Mapper-type algorithms. We derive theoretical results that provide estimates for the instability and suggest practical ways to control it. We provide also experiments to illustrate our results and in particular we demonstrate that a reliable candidate Mapper output can be identified as a local minimum of instability regarded as a function of Mapper input parameters.
Continuous-Time Birth-Death MCMC for Bayesian Regression Tree Models
http://jmlr.org/papers/v21/19-307.html
2020Reza Mohammadi, Matthew Pratola, Maurits Kaptein
Decision trees are flexible models that are well suited for many statistical regression problems. In the Bayesian framework for regression trees, Markov Chain Monte Carlo (MCMC) search algorithms are required to generate samples of tree models according to their posterior probabilities. The critical component of such MCMC algorithms is to construct "good" Metropolis-Hastings steps to update the tree topology. Such algorithms frequently suffer from poor mixing and local mode stickiness; therefore, the algorithms are slow to converge. Hitherto, authors have primarily used discrete-time birth/death mechanisms for Bayesian (sums of) regression tree models to explore the tree-model space. These algorithms are efficient, in terms of computation and convergence, only if the rejection rate is low which is not always the case. We overcome this issue by developing a novel search algorithm which is based on a continuous-time birth-death Markov process. The search algorithm explores the tree-model space by jumping between parameter spaces corresponding to different tree structures. The jumps occur in continuous time corresponding to the birth-death events which are modeled as independent Poisson processes. In the proposed algorithm, the moves between models are always accepted which can dramatically improve the convergence and mixing properties of the search algorithm. We provide theoretical support of the algorithm for Bayesian regression tree models and demonstrate its performance in a simulated example.
Empirical Risk Minimization in the Non-interactive Local Model of Differential Privacy
http://jmlr.org/papers/v21/19-253.html
2020Di Wang, Marco Gaboardi, Adam Smith, Jinhui Xu
In this paper, we study the Empirical Risk Minimization (ERM) problem in the non-interactive Local Differential Privacy (LDP) model. Previous research on this problem (Smith et al., 2017) indicates that the sample complexity, to achieve error $\alpha$, needs to be exponentially depending on the dimensionality $p$ for general loss functions. In this paper, we make two attempts to resolve this issue by investigating conditions on the loss functions that allow us to remove such a limit. In our first attempt, we show that if the loss function is $(\infty, T)$-smooth, by using the Bernstein polynomial approximation we can avoid the exponential dependency in the term of $\alpha$. We then propose player-efficient algorithms with $1$-bit communication complexity and $O(1)$ computation cost for each player. The error bound of these algorithms is asymptotically the same as the original one. With some additional assumptions, we also give an algorithm which is more efficient for the server. In our second attempt, we show that for any $1$-Lipschitz generalized linear convex loss function, there is an $(\epsilon, \delta)$-LDP algorithm whose sample complexity for achieving error $\alpha$ is only linear in the dimensionality $p$. Our results use a polynomial of inner product approximation technique. Finally, motivated by the idea of using polynomial approximation and based on different types of polynomial approximations, we propose (efficient) non-interactive locally differentially private algorithms for learning the set of k-way marginal queries and the set of smooth queries.
Asymptotic Analysis via Stochastic Differential Equations of Gradient Descent Algorithms in Statistical and Computational Paradigms
http://jmlr.org/papers/v21/19-245.html
2020Yazhen Wang, Shang Wu
This paper investigates the asymptotic behaviors of gradient descent algorithms (particularly accelerated gradient descent and stochastic gradient descent) in the context of stochastic optimization arising in statistics and machine learning, where objective functions are estimated from available data. We show that these algorithms can be computationally modeled by continuous-time ordinary or stochastic differential equations. We establish gradient flow central limit theorems to describe the limiting dynamic behaviors of these computational algorithms and the large-sample performances of the related statistical procedures, as the number of algorithm iterations and data size both go to infinity, where the gradient flow central limit theorems are governed by some linear ordinary or stochastic differential equations, like time-dependent Ornstein-Uhlenbeck processes. We illustrate that our study can provide a novel unified framework for a joint computational and statistical asymptotic analysis, where the computational asymptotic analysis studies the dynamic behaviors of these algorithms with time (or the number of iterations in the algorithms), the statistical asymptotic analysis investigates the large-sample behaviors of the statistical procedures (like estimators and classifiers) that are computed by applying the algorithms; in fact, the statistical procedures are equal to the limits of the random sequences generated from these iterative algorithms, as the number of iterations goes to infinity. The joint analysis results based on the obtained gradient flow central limit theorems lead to the identification of four factors---learning rate, batch size, gradient covariance, and Hessian---to derive new theories regarding the local minima found by stochastic gradient descent for solving non-convex optimization problems.
Reinforcement Learning in Continuous Time and Space: A Stochastic Control Approach
http://jmlr.org/papers/v21/19-144.html
2020Haoran Wang, Thaleia Zariphopoulou, Xun Yu Zhou
We consider reinforcement learning (RL) in continuous time with continuous feature and action spaces. We motivate and devise an exploratory formulation for the feature dynamics that captures learning under exploration, with the resulting optimization problem being a revitalization of the classical relaxed stochastic control. We then study the problem of achieving the best trade-off between exploration and exploitation by considering an entropy-regularized reward function. We carry out a complete analysis of the problem in the linear--quadratic (LQ) setting and deduce that the optimal feedback control distribution for balancing exploitation and exploration is Gaussian. This in turn interprets the widely adopted Gaussian exploration in RL, beyond its simplicity for sampling. Moreover, the exploitation and exploration are captured respectively by the mean and variance of the Gaussian distribution. We characterize the cost of exploration, which, for the LQ case, is shown to be proportional to the entropy regularization weight and inversely proportional to the discount rate. Finally, as the weight of exploration decays to zero, we prove the convergence of the solution of the entropy-regularized LQ problem to the one of the classical LQ problem.
A determinantal point process for column subset selection
http://jmlr.org/papers/v21/19-080.html
2020Ayoub Belhadji, Rémi Bardenet, Pierre Chainais
Two popular approaches to dimensionality reduction are principal component analysis, which projects onto a small number of well-chosen but non-interpretable directions, and feature selection, which selects a small number of the original features. Feature selection can be abstracted as selecting the subset of columns of a matrix $X \in \mathbb{R}^{N \times d}$ which minimize the approximation error, i.e., the norm of the residual after projecting $X$ onto the space spanned by the selected columns. Such a combinatorial optimization is usually impractical, and there has been interest in polynomial-cost, random subset selection algorithms that favour small values of this approximation error. We propose sampling from a projection determinantal point process, a repulsive distribution over column indices that favours diversity among the selected columns. We bound the ratio of the expected approximation error over the optimal error of PCA. These bounds improve over the state-of-the-art bounds of volume sampling when some realistic structural assumptions are satisfied for $X$. Numerical experiments suggest that our bounds are tight, and that our algorithms have comparable performance with the double phase algorithm, often considered the practical state-of-the-art.
Successor Features Combine Elements of Model-Free and Model-based Reinforcement Learning
http://jmlr.org/papers/v21/19-060.html
2020Lucas Lehnert, Michael L. Littman
A key question in reinforcement learning is how an intelligent agent can generalize knowledge across different inputs. By generalizing across different inputs, information learned for one input can be immediately reused for improving predictions for another input. Reusing information allows an agent to compute an optimal decision-making strategy using less data. State representation is a key element of the generalization process, compressing a high-dimensional input space into a low-dimensional latent state space. This article analyzes properties of different latent state spaces, leading to new connections between model-based and model-free reinforcement learning. Successor features, which predict frequencies of future observations, form a link between model-based and model-free learning: Learning to predict future expected reward outcomes, a key characteristic of model-based agents, is equivalent to learning successor features. Learning successor features is a form of temporal difference learning and is equivalent to learning to predict a single policy's utility, which is a characteristic of model-free agents. Drawing on the connection between model-based reinforcement learning and successor features, we demonstrate that representations that are predictive of future reward outcomes generalize across variations in both transitions and rewards. This result extends previous work on successor features, which is constrained to fixed transitions and assumes re-learning of the transferred state representation.
Conic Optimization for Quadratic Regression Under Sparse Noise
http://jmlr.org/papers/v21/18-881.html
2020Igor Molybog, Ramtin Madani, Javad Lavaei
This paper is concerned with the quadratic regression problem, where the goal is to find the unknown state (numerical parameters) of a system modeled by a set of equations that are quadratic in the state. We focus on the setting when a subset of equations of fixed cardinality is subject to errors of arbitrary magnitudes (potentially adversarial). We develop two methods to address this problem, which are both based on conic optimization and are able to accept any available prior knowledge on the solution as an input. We derive sufficient conditions for guaranteeing the correct recovery of the unknown state for each method and show that one method provides a better accuracy while the other one scales better to large-scale systems. The obtained conditions consist in bounds on the number of bad measurements each method can tolerate without producing a nonzero estimation error. In the case when no prior knowledge is available, we develop an iterative-based conic optimization technique. It is proved that the proposed methods allow up to half of the total number of measurements to be grossly erroneous.The efficacy of the developed methods is demonstrated in different case studies, including data analytics for a European power grid.
Contextual Explanation Networks
http://jmlr.org/papers/v21/18-856.html
2020Maruan Al-Shedivat, Avinava Dubey, Eric Xing
Modern learning algorithms excel at producing accurate but complex models of the data. However, deploying such models in the real-world requires extra care: we must ensure their reliability, robustness, and absence of undesired biases. This motivates the development of models that are equally accurate but can be also easily inspected and assessed beyond their predictive performance. To this end, we introduce contextual explanation networks (CENs)---a class of architectures that learn to predict by generating and utilizing intermediate, simplified probabilistic models. Specifically, CENs generate parameters for intermediate graphical models which are further used for prediction and play the role of explanations. Contrary to the existing post-hoc model-explanation tools, CENs learn to predict and to explain simultaneously. Our approach offers two major advantages: (i) for each prediction, valid, instance-specific explanation is generated with no computational overhead and (ii) prediction via explanation acts as a regularizer and boosts performance in data-scarce settings. We analyze the proposed framework theoretically and experimentally. Our results on image and text classification and survival analysis tasks demonstrate that CENs are not only competitive with the state-of-the-art methods but also offer additional insights behind each prediction, that can be valuable for decision support. We also show that while post-hoc methods may produce misleading explanations in certain cases, CENs are consistent and allow to detect such cases systematically.
Learning and Interpreting Multi-Multi-Instance Learning Networks
http://jmlr.org/papers/v21/18-811.html
2020Alessandro Tibo, Manfred Jaeger, Paolo Frasconi
We introduce an extension of the multi-instance learning problem where examples are organized as nested bags of instances (e.g., a document could be represented as a bag of sentences, which in turn are bags of words). This framework can be useful in various scenarios, such as text and image classification, but also supervised learning over graphs. As a further advantage, multi-multi instance learning enables a particular way of interpreting predictions and the decision function. Our approach is based on a special neural network layer, called bag-layer, whose units aggregate bags of inputs of arbitrary size. We prove theoretically that the associated class of functions contains all Boolean functions over sets of sets of instances and we provide empirical evidence that functions of this kind can be actually learned on semi-synthetic datasets. We finally present experiments on text classification, on citation graphs, and social graph data, which show that our model obtains competitive results with respect to accuracy when compared to other approaches such as convolutional networks on graphs, while at the same time it supports a general approach to interpret the learnt model, as well as explain individual predictions.
Semi-parametric Learning of Structured Temporal Point Processes
http://jmlr.org/papers/v21/18-735.html
2020Ganggang Xu, Ming Wang, Jiangze Bian, Hui Huang, Timothy R. Burch, Sandro C. Andrade, Jingfei Zhang, Yongtao Guan
We propose a general framework of using a multi-level log-Gaussian Cox process to model repeatedly observed point processes with complex structures; such type of data has become increasingly available in various areas including medical research, social sciences, economics, and finance due to technological advances. A novel nonparametric approach is developed to efficiently and consistently estimate the covariance functions of the latent Gaussian processes at all levels. To predict the functional principal component scores, we propose a consistent estimation procedure by maximizing the conditional likelihood of super-positions of point processes. We further extend our procedure to the bivariate point process case in which potential correlations between the processes can be assessed. Asymptotic properties of the proposed estimators are investigated, and the effectiveness of our procedures is illustrated through a simulation study and an application to a stock trading dataset.
Adaptive Smoothing for Path Integral Control
http://jmlr.org/papers/v21/18-624.html
2020Dominik Thalmeier, Hilbert J. Kappen, Simone Totaro, Vicenç Gómez
In Path Integral control problems a representation of an optimally controlled dynamical system can be formally computed and serve as a guidepost to learn a parametrized policy. The Path Integral Cross-Entropy (PICE) method tries to exploit this, but is hampered by poor sample efficiency. We propose a model-free algorithm called ASPIC (Adaptive Smoothing of Path Integral Control) that applies an inf-convolution to the cost function to speedup convergence of policy optimization. We identify PICE as the infinite smoothing limit of such technique and show that the sample efficiency problems that PICE suffers disappear for finite levels of smoothing. For zero smoothing, ASPIC becomes a greedy optimization of the cost, which is the standard approach in current reinforcement learning. ASPIC adapts the smoothness parameter to keep the variance of the gradient estimator at a predefined level, independently of the number of samples. We show analytically and empirically that intermediate levels of smoothing are optimal, which renders the new method superior to both PICE and direct cost optimization.
A Unified q-Memorization Framework for Asynchronous Stochastic Optimization
http://jmlr.org/papers/v21/18-434.html
2020Bin Gu, Wenhan Xian, Zhouyuan Huo, Cheng Deng, Heng Huang
Asynchronous stochastic algorithms with various variance reduction techniques (such as SVRG, S2GD, SAGA and q-SAGA) are popular in solving large scale learning problems. Recently, Reddi et al. (2015) proposed an unified variance reduction framework (i.e., HSAG) to analyze the asynchronous stochastic gradient optimization. However, the HSAG framework cannot incorporate the S2GD technique, the analysis of the HSAG framework is limited to the SVRG and SAGA techniques on the smooth convex optimization. They did not analyze other important various variance techniques (e.g., S2GD and q-SAGA) and other important optimization problems (e.g., convex optimization with non-smooth regularization and non-convex optimization with cardinality constraint). In this paper, we bridge this gap by using an unified q-memorization framework for various variance reduction techniques (including SVRG, S2GD, SAGA, q-SAGA) to analyze asynchronous stochastic algorithms for three important optimization problems. Specifically, based on the q-memorization framework, 1) we propose an asynchronous stochastic gradient hard thresholding algorithm with q-memorization (AsySGHT-qM) for the non-convex optimization with cardinality constraint, and prove that the convergence rate of AsySGHT-qM before reaching the inherent error induced by gradient hard thresholding methods is geometric. 2) We propose an asynchronous stochastic proximal gradient algorithm (AsySPG-qM) for the convex optimization with non-smooth regularization, and prove that AsySPG-qM can achieve a linear convergence rate. 3) We propose an asynchronous stochastic gradient descent algorithm (AsySGD-qM) for the general non-convex optimization problem, and prove that AsySGD-qM can achieve a sublinear convergence rate to stationary points. The experimental results on various large-scale datasets confirm the fast convergence of our AsySGHT-qM, AsySPG-qM and AsySGD-qM through concrete realizations of SVRG and SAGA.
Beyond Trees: Classification with Sparse Pairwise Dependencies
http://jmlr.org/papers/v21/18-348.html
2020Yaniv Tenzer, Amit Moscovich, Mary Frances Dorn, Boaz Nadler, Clifford Spiegelman
Several classification methods assume that the underlying distributions follow tree-structured graphical models. Indeed, trees capture statistical dependencies between pairs of variables, which may be crucial to attaining low classification errors. In this setting, the optimal classifier is linear in the log-transformed univariate and bivariate densities that correspond to the tree edges. In practice, observed data may not be well approximated by trees. Yet, motivated by the importance of pairwise dependencies for accurate classification, here we propose to approximate the optimal decision boundary by a sparse linear combination of the univariate and bivariate log-transformed densities. Our proposed approach is semi-parametric in nature: we non-parametrically estimate the univariate and bivariate densities, remove pairs of variables that are nearly independent using the Hilbert-Schmidt independence criterion, and finally construct a linear SVM using the retained log-transformed densities. We demonstrate on synthetic and real data sets, that our classifier, named SLB (sparse log-bivariate density), is competitive with other popular classification methods.
Efficient Adjustment Sets for Population Average Causal Treatment Effect Estimation in Graphical Models
http://jmlr.org/papers/v21/19-1026.html
2020Andrea Rotnitzky, Ezequiel Smucler
The method of covariate adjustment is often used for estimation of total treatment effects from observational studies. Restricting attention to causal linear models, a recent article (Henckel et al., 2019) derived two novel graphical criteria: one to compare the asymptotic variance of linear regression treatment effect estimators that control for certain distinct adjustment sets and another to identify the optimal adjustment set that yields the least squares estimator with the smallest asymptotic variance. In this paper we show that the same graphical criteria can be used in non-parametric causal graphical models when treatment effects are estimated using non-parametrically adjusted estimators of the interventional means. We also provide a new graphical criterion for determining the optimal adjustment set among the minimal adjustment sets and another novel graphical criterion for comparing time dependent adjustment sets. We show that uniformly optimal time dependent adjustment sets do not always exist. For point interventions, we provide a sound and complete graphical criterion for determining when a non-parametric optimally adjusted estimator of an interventional mean, or of a contrast of interventional means, is semiparametric efficient under the non-parametric causal graphical model. In addition, when the criterion is not met, we provide a sound algorithm that checks for possible simplifications of the efficient influence function of the parameter. Finally, we find an interesting connection between identification and efficient covariate adjustment estimation. Specifically, we show that if there exists an identifying formula for an interventional mean that depends only on treatment, outcome and mediators, then the non-parametric optimally adjusted estimator can never be globally efficient under the causal graphical model.
Kriging Prediction with Isotropic Matern Correlations: Robustness and Experimental Designs
http://jmlr.org/papers/v21/19-1045.html
2020Rui Tuo, Wenjia Wang
This work investigates the prediction performance of the kriging predictors. We derive some error bounds for the prediction error in terms of non-asymptotic probability under the uniform metric and $L_p$ metrics when the spectral densities of both the true and the imposed correlation functions decay algebraically. The Matern family is a prominent class of correlation functions of this kind. Our analysis shows that, when the smoothness of the imposed correlation function exceeds that of the true correlation function, the prediction error becomes more sensitive to the space-filling property of the design points. In particular, the kriging predictor can still reach the optimal rate of convergence, if the experimental design scheme is quasi-uniform. Lower bounds of the kriging prediction error are also derived under the uniform metric and $L_p$ metrics. An accurate characterization of this error is obtained, when an oversmoothed correlation function and a space-filling design is used.
Consistency of Semi-Supervised Learning Algorithms on Graphs: Probit and One-Hot Methods
http://jmlr.org/papers/v21/15-900.html
2020Franca Hoffmann, Bamdad Hosseini, Zhi Ren, Andrew M Stuart
Graph-based semi-supervised learning is the problem of propagating labels from a small number of labelled data points to a larger set of unlabelled data. This paper is concerned with the consistency of optimization-based techniques for such problems, in the limit where the labels have small noise and the underlying unlabelled data is well clustered. We study graph-based probit for binary classification, and a natural generalization of this method to multi-class classification using one-hot encoding. The resulting objective function to be optimized comprises the sum of a quadratic form defined through a rational function of the graph Laplacian, involving only the unlabelled data, and a fidelity term involving only the labelled data. The consistency analysis sheds light on the choice of the rational function defining the optimization.
Scikit-network: Graph Analysis in Python
http://jmlr.org/papers/v21/20-412.html
2020Thomas Bonald, Nathan de Lara, Quentin Lutz, Bertrand Charpentier
Scikit-network is a Python package inspired by scikit-learn for the analysis of large graphs. Graphs are represented by their adjacency matrix in the sparse CSR format of SciPy. The package provides state-of-the-art algorithms for ranking, clustering, classifying, embedding and visualizing the nodes of a graph. High performance is achieved through a mix of fast matrix-vector products (using SciPy), compiled code (using Cython) and parallel processing. The package is distributed under the BSD license, with dependencies limited to NumPy and SciPy. It is compatible with Python 3.6 and newer. Source code, documentation and installation instructions are available online.
Topology of Deep Neural Networks
http://jmlr.org/papers/v21/20-345.html
2020Gregory Naitzat, Andrey Zhitnikov, Lek-Heng Lim
We study how the topology of a data set $M = M_a \cup M_b \subseteq \mathbb{R}^d$, representing two classes $a$ and $b$ in a binary classification problem, changes as it passes through the layers of a well-trained neural network, i.e., one with perfect accuracy on training set and near-zero generalization error ($\approx 0.01\%$). The goal is to shed light on two mysteries in deep neural networks: (i) a nonsmooth activation function like ReLU outperforms a smooth one like hyperbolic tangent; (ii) successful neural network architectures rely on having many layers, even though a shallow network can approximate any function arbitrarily well. We performed extensive experiments on the persistent homology of a wide range of point cloud data sets, both real and simulated. The results consistently demonstrate the following: (1) Neural networks operate by changing topology, transforming a topologically complicated data set into a topologically simple one as it passes through the layers. No matter how complicated the topology of $M$ we begin with, when passed through a well-trained neural network $f : \mathbb{R}^d \to \mathbb{R}^p$, there is a vast reduction in the Betti numbers of both components $M_a$ and $M_b$; in fact they nearly always reduce to their lowest possible values: $\beta_k\bigl(f(M_i)\bigr) = 0$ for $k \ge 1$ and $\beta_0\bigl(f(M_i)\bigr) = 1$, $i =a, b$. (2) The reduction in Betti numbers is significantly faster for ReLU activation than for hyperbolic tangent activation as the former defines nonhomeomorphic maps that change topology, whereas the latter defines homeomorphic maps that preserve topology. (3) Shallow and deep networks transform data sets differently --- a shallow network operates mainly through changing geometry and changes topology only in its final layers, a deep one spreads topological changes more evenly across all layers.
Near-optimal Individualized Treatment Recommendations
http://jmlr.org/papers/v21/20-334.html
2020Haomiao Meng, Ying-Qi Zhao, Haoda Fu, Xingye Qiao
The individualized treatment recommendation (ITR) is an important analytic framework for precision medicine. The goal of ITR is to assign the best treatments to patients based on their individual characteristics. From the machine learning perspective, the solution to the ITR problem can be formulated as a weighted classification problem to maximize the mean benefit from the recommended treatments given patients' characteristics. Several ITR methods have been proposed in both the binary setting and the multicategory setting. In practice, one may prefer a more flexible recommendation that includes multiple treatment options. This motivates us to develop methods to obtain a set of near-optimal individualized treatment recommendations alternative to each other, called alternative individualized treatment recommendations (A-ITR). We propose two methods to estimate the optimal A-ITR within the outcome weighted learning (OWL) framework. Simulation studies and a real data analysis for Type 2 diabetic patients with injectable antidiabetic treatments are conducted to show the usefulness of the proposed A-ITR framework. We also show the consistency of these methods and obtain an upper bound for the risk between the theoretically optimal recommendation and the estimated one. An R package "aitr" has been developed, found at https://github.com/menghaomiao/aitr.
Distributed High-dimensional Regression Under a Quantile Loss Function
http://jmlr.org/papers/v21/20-297.html
2020Xi Chen, Weidong Liu, Xiaojun Mao, Zhuoyi Yang
This paper studies distributed estimation and support recovery for high-dimensional linear regression model with heavy-tailed noise. To deal with heavy-tailed noise whose variance can be infinite, we adopt the quantile regression loss function instead of the commonly used squared loss. However, the non-smooth quantile loss poses new challenges to high-dimensional distributed estimation in both computation and theoretical development. To address the challenge, we transform the response variable and establish a new connection between quantile regression and ordinary linear regression. Then, we provide a distributed estimator that is both computationally and communicationally efficient, where only the gradient information is communicated at each iteration. Theoretically, we show that, after a constant number of iterations, the proposed estimator achieves a near-oracle convergence rate without any restriction on the number of machines. Moreover, we establish the theoretical guarantee for the support recovery. The simulation analysis is provided to demonstrate the effectiveness of our method.
Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
http://jmlr.org/papers/v21/20-212.html
2020Sanmit Narvekar, Bei Peng, Matteo Leonetti, Jivko Sinapov, Matthew E. Taylor, Peter Stone
Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. Despite many advances over the past three decades, learning in many domains still requires a large amount of interaction with the environment, which can be prohibitively expensive in realistic scenarios. To address this problem, transfer learning has been applied to reinforcement learning such that experience gained in one task can be leveraged when starting to learn the next, harder task. More recently, several lines of research have explored how tasks, or data samples themselves, can be sequenced into a curriculum for the purpose of learning a problem that may otherwise be too difficult to learn from scratch. In this article, we present a framework for curriculum learning (CL) in reinforcement learning, and use it to survey and classify existing CL methods in terms of their assumptions, capabilities, and goals. Finally, we use our framework to find open problems and suggest directions for future RL curriculum learning research.
Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction
http://jmlr.org/papers/v21/20-210.html
2020Boyue Li, Shicong Cen, Yuxin Chen, Yuejie Chi
There is growing interest in large-scale machine learning and optimization over decentralized networks, e.g. in the context of multi-agent learning and federated learning. Due to the imminent need to alleviate the communication burden, the investigation of communication-efficient distributed optimization algorithms --- particularly for empirical risk minimization --- has flourished in recent years. A large fraction of these algorithms have been developed for the master/slave setting, relying on the presence of a central parameter server that can communicate with all agents. This paper focuses on distributed optimization over networks, or decentralized optimization, where each agent is only allowed to aggregate information from its neighbors over a network (namely, no centralized coordination is present). By properly adjusting the global gradient estimate via local averaging in conjunction with proper correction, we develop a communication-efficient approximate Newton-type method, called Network-DANE, which generalizes DANE to accommodate decentralized scenarios. Our key ideas can be applied, in a systematic manner, to obtain decentralized versions of other master/slave distributed algorithms. A notable development is Network-SVRG/SARAH, which employs variance reduction at each agent to further accelerate local computation. We establish linear convergence of Network-DANE and Network-SVRG for strongly convex losses, and Network-SARAH for quadratic losses, which shed light on the impacts of data homogeneity, network connectivity, and local averaging upon the rate of convergence. We further extend Network-DANE to composite optimization by allowing a nonsmooth penalty term. Numerical evidence is provided to demonstrate the appealing performance of our algorithms over competitive baselines, in terms of both communication and computation efficiency. Our work suggests that by performing a judiciously chosen amount of local communication and computation per iteration, the overall efficiency can be substantially improved.
Variational Inference for Computational Imaging Inverse Problems
http://jmlr.org/papers/v21/20-151.html
2020Francesco Tonolini, Jack Radford, Alex Turpin, Daniele Faccio, Roderick Murray-Smith
Machine learning methods for computational imaging require uncertainty estimation to be reliable in real settings. While Bayesian models offer a computationally tractable way of recovering uncertainty, they need large data volumes to be trained, which in imaging applications implicates prohibitively expensive collections with specific imaging instruments. This paper introduces a novel framework to train variational inference for inverse problems exploiting in combination few experimentally collected data, domain expertise and existing image data sets. In such a way, Bayesian machine learning models can solve imaging inverse problems with minimal data collection efforts. Extensive simulated experiments show the advantages of the proposed framework. The approach is then applied to two real experimental optics settings: holographic image reconstruction and imaging through highly scattering media. In both settings, state of the art reconstructions are achieved with little collection of training data.
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
http://jmlr.org/papers/v21/20-081.html
2020Tabish Rashid, Mikayel Samvelyan, Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, Shimon Whiteson
In many real-world settings, a team of agents must coordinate its behaviour while acting in a decentralised fashion. At the same time, it is often possible to train the agents in a centralised fashion where global state information is available and communication constraints are lifted. Learning joint action-values conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised policies in a centralised end-to-end fashion. QMIX employs a mixing network that estimates joint action-values as a monotonic combination of per-agent values. We structurally enforce that the joint-action value is monotonic in the per-agent values, through the use of non-negative weights in the mixing network, which guarantees consistency between the centralised and decentralised policies. To evaluate the performance of QMIX, we propose the StarCraft Multi-Agent Challenge (SMAC) as a new benchmark for deep multi-agent reinforcement learning. We evaluate QMIX on a challenging set of SMAC scenarios and show that it significantly outperforms existing multi-agent reinforcement learning methods.
Optimal Estimation of Sparse Topic Models
http://jmlr.org/papers/v21/20-079.html
2020Xin Bing, Florentina Bunea, Marten Wegkamp
Topic models have become popular tools for dimension reduction and exploratory analysis of text data which consists in observed frequencies of a vocabulary of $p$ words in $n$ documents, stored in a $p\times n$ matrix. The main premise is that the mean of this data matrix can be factorized into a product of two non-negative matrices: a $p\times K$ word-topic matrix $A$ and a $K\times n$ topic-document matrix $W$. This paper studies the estimation of $A$ that is possibly element-wise sparse, and the number of topics $K$ is unknown. In this under-explored context, we derive a new minimax lower bound for the estimation of such $A$ and propose a new computationally efficient algorithm for its recovery. We derive a finite sample upper bound for our estimator, and show that it matches the minimax lower bound in many scenarios. Our estimate adapts to the unknown sparsity of $A$ and our analysis is valid for any finite $n$, $p$, $K$ and document lengths. Empirical results on both synthetic data and semi-synthetic data show that our proposed estimator is a strong competitor of the existing state-of-the-art algorithms for both non-sparse $A$ and sparse $A$, and has superior performance is many scenarios of interest.
Breaking the Curse of Nonregularity with Subagging --- Inference of the Mean Outcome under Optimal Treatment Regimes
http://jmlr.org/papers/v21/20-066.html
2020Chengchun Shi, Wenbin Lu, Rui Song
Precision medicine is an emerging medical approach that allows physicians to select the treatment options based on individual patient information. The goal of precision medicine is to identify the optimal treatment regime (OTR) that yields the most favorable clinical outcome. Prior to adopting any OTR in clinical practice, it is crucial to know the impact of implementing such a policy. Although considerable research has been devoted to estimating the OTR in the literature, less attention has been paid to statistical inference of the OTR. Challenges arise in the nonregular cases where the OTR is not uniquely defined. To deal with nonregularity, we develop a novel inference method for the mean outcome under an OTR (the optimal value function) based on subsample aggregating (subagging). The proposed method can be applied to multi-stage studies where treatments are sequentially assigned over time. Bootstrap aggregating (bagging) and subagging have been recognized as effective vari- ance reduction techniques to improve unstable estimators or classifiers (Buhlmann and Yu, 2002). However, it remains unknown whether these approaches can yield valid inference results. We show the proposed confidence interval (CI) for the optimal value function achieves nominal coverage. In addition, due to the variance reduction effect of subagging, our method enjoys certain statistical optimality. Specifically, we show that the mean squared error of the proposed value estimator is strictly smaller than that based on the simple sample-splitting estimator in the nonregular cases. Moreover, under certain conditions, the length of our proposed CI is shown to be on average shorter than CIs constructed based on the existing state-of-the-art method (Luedtke and van der Laan, 2016) and the 'oracle' method which works as well as if an OTR were known. Extensive numerical studies are conducted to back up our theoretical findings.
Wide Neural Networks with Bottlenecks are Deep Gaussian Processes
http://jmlr.org/papers/v21/20-017.html
2020Devanshu Agrawal, Theodore Papamarkou, Jacob Hinkle
There has recently been much work on the "wide limit" of neural networks, where Bayesian neural networks (BNNs) are shown to converge to a Gaussian process (GP) as all hidden layers are sent to infinite width. However, these results do not apply to architectures that require one or more of the hidden layers to remain narrow. In this paper, we consider the wide limit of BNNs where some hidden layers, called "bottlenecks", are held at finite width. The result is a composition of GPs that we term a "bottleneck neural network Gaussian process" (bottleneck NNGP). Although intuitive, the subtlety of the proof is in showing that the wide limit of a composition of networks is in fact the composition of the limiting GPs. We also analyze theoretically a single-bottleneck NNGP, finding that the bottleneck induces dependence between the outputs of a multi-output network that persists through extreme post-bottleneck depths, and prevents the kernel of the network from losing discriminative power at extreme post-bottleneck depths.
Adaptive Approximation and Generalization of Deep Neural Network with Intrinsic Dimensionality
http://jmlr.org/papers/v21/20-002.html
2020Ryumei Nakada, Masaaki Imaizumi
In this study, we prove that an intrinsic low dimensionality of covariates is the main factor that determines the performance of deep neural networks (DNNs). DNNs generally provide outstanding empirical performance. Hence, numerous studies have actively investigated the theoretical properties of DNNs to understand their underlying mechanisms. In particular, the behavior of DNNs in terms of high-dimensional data is one of the most critical questions. However, this issue has not been sufficiently investigated from the aspect of covariates, although high-dimensional data have practically low intrinsic dimensionality. In this study, we derive bounds for an approximation error and a generalization error regarding DNNs with intrinsically low dimensional covariates. We apply the notion of the Minkowski dimension and develop a novel proof technique. Consequently, we show that convergence rates of the errors by DNNs do not depend on the nominal high dimensionality of data, but on its lower intrinsic dimension. We further prove that the rate is optimal in the minimax sense. We identify an advantage of DNNs by showing that DNNs can handle a broader class of intrinsic low dimensional data than other adaptive estimators. Finally, we conduct a numerical simulation to validate the theoretical results.
Doubly Distributed Supervised Learning and Inference with High-Dimensional Correlated Outcomes
http://jmlr.org/papers/v21/19-996.html
2020Emily C. Hector, Peter X.-K. Song
This paper presents a unified framework for supervised learning and inference procedures using the divide-and-conquer approach for high-dimensional correlated outcomes. We propose a general class of estimators that can be implemented in a fully distributed and parallelized computational scheme. Modeling, computational and theoretical challenges related to high-dimensional correlated outcomes are overcome by dividing data at both outcome and subject levels, estimating the parameter of interest from blocks of data using a broad class of supervised learning procedures, and combining block estimators in a closed-form meta-estimator asymptotically equivalent to estimates obtained by Hansen (1982)'s generalized method of moments (GMM) that does not require the entire data to be reloaded on a common server. We provide rigorous theoretical justifications for the use of distributed estimators with correlated outcomes by studying the asymptotic behaviour of the combined estimator with fixed and diverging number of data divisions. Simulations illustrate the finite sample performance of the proposed method, and we provide an R package for ease of implementation.
Krylov Subspace Method for Nonlinear Dynamical Systems with Random Noise
http://jmlr.org/papers/v21/19-993.html
2020Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda, Yoichi Matsuo, Yoshinobu Kawahara
Operator-theoretic analysis of nonlinear dynamical systems has attracted much attention in a variety of engineering and scientific fields, endowed with practical estimation methods using data such as dynamic mode decomposition. In this paper, we address a lifted representation of nonlinear dynamical systems with random noise based on transfer operators, and develop a novel Krylov subspace method for estimating the operators using finite data, with consideration of the unboundedness of operators. For this purpose, we first consider Perron-Frobenius operators with kernel-mean embeddings for such systems. We then extend the Arnoldi method, which is the most classical type of Kryov subspace methods, so that it can be applied to the current case. Meanwhile, the Arnoldi method requires the assumption that the operator is bounded, which is not necessarily satisfied for transfer operators on nonlinear systems. We accordingly develop the shift-invert Arnoldi method for Perron-Frobenius operators to avoid this problem. Also, we describe an approach of evaluating predictive accuracy by estimated operators on the basis of the maximum mean discrepancy, which is applicable, for example, to anomaly detection in complex systems. The empirical performance of our methods is investigated using synthetic and real-world healthcare data.
Randomization as Regularization: A Degrees of Freedom Explanation for Random Forest Success
http://jmlr.org/papers/v21/19-905.html
2020Lucas Mentch, Siyu Zhou
Random forests remain among the most popular off-the-shelf supervised machine learning tools with a well-established track record of predictive accuracy in both regression and classification settings. Despite their empirical success as well as a bevy of recent work investigating their statistical properties, a full and satisfying explanation for their success has yet to be put forth. Here we aim to take a step forward in this direction by demonstrating that the additional randomness injected into individual trees serves as a form of implicit regularization, making random forests an ideal model in low signal-to-noise ratio (SNR) settings. Specifically, from a model-complexity perspective, we show that the mtry parameter in random forests serves much the same purpose as the shrinkage penalty in explicitly regularized regression procedures like lasso and ridge regression. To highlight this point, we design a randomized linear-model-based forward selection procedure intended as an analogue to tree-based random forests and demonstrate its surprisingly strong empirical performance. Numerous demonstrations on both real and synthetic data are provided.
Rationally Inattentive Inverse Reinforcement Learning Explains YouTube Commenting Behavior
http://jmlr.org/papers/v21/19-872.html
2020William Hoiles, Vikram Krishnamurthy, Kunal Pattanayak
We consider a novel application of inverse reinforcement learning with behavioral economics constraints to model, learn and predict the commenting behavior of YouTube viewers. Each group of users is modeled as a rationally inattentive Bayesian agent which solves a contextual bandit problem. Our methodology integrates three key components. First, to identify distinct commenting patterns, we use deep embedded clustering to estimate framing information (essential extrinsic features) that clusters users into distinct groups. Second, we present an inverse reinforcement learning algorithm that uses Bayesian revealed preferences to test for rationality: does there exist a utility function that rationalizes the given data, and if yes, can it be used to predict commenting behavior? Finally, we impose behavioral economics constraints stemming from rational inattention to characterize the attention span of groups of users. The test imposes a Renyi mutual information cost constraint which impacts how the agent can select attention strategies to maximize their expected utility. After a careful analysis of a massive YouTube dataset, our surprising result is that in most YouTube user groups, the commenting behavior is consistent with optimizing a Bayesian utility with rationally inattentive constraints. The paper also highlights how the rational inattention model can accurately predict commenting behavior. The massive YouTube dataset and analysis used in this paper are available on GitHub and completely reproducible.
The Optimal Ridge Penalty for Real-world High-dimensional Data Can Be Zero or Negative due to the Implicit Ridge Regularization
http://jmlr.org/papers/v21/19-844.html
2020Dmitry Kobak, Jonathan Lomond, Benoit Sanchez
A conventional wisdom in statistical learning is that large models require strong regularization to prevent overfitting. Here we show that this rule can be violated by linear regression in the underdetermined $n\ll p$ situation under realistic conditions. Using simulations and real-life high-dimensional datasets, we demonstrate that an explicit positive ridge penalty can fail to provide any improvement over the minimum-norm least squares estimator. Moreover, the optimal value of ridge penalty in this situation can be negative. This happens when the high-variance directions in the predictor space can predict the response variable, which is often the case in the real-world high-dimensional data. In this regime, low-variance directions provide an implicit ridge regularization and can make any further positive ridge penalty detrimental. We prove that augmenting any linear model with random covariates and using minimum-norm estimator is asymptotically equivalent to adding the ridge penalty. We use a spiked covariance model as an analytically tractable example and prove that the optimal ridge penalty in this case is negative when $n\ll p$.
Convex and Non-Convex Approaches for Statistical Inference with Class-Conditional Noisy Labels
http://jmlr.org/papers/v21/19-833.html
2020Hyebin Song, Ran Dai, Garvesh Raskutti, Rina Foygel Barber
We study the problem of estimation and testing in logistic regression with class-conditional noise in the observed labels, which has an important implication in the Positive-Unlabeled (PU) learning setting. With the key observation that the label noise problem belongs to a special sub-class of generalized linear models (GLM), we discuss convex and non-convex approaches that address this problem. A non-convex approach based on the maximum likelihood estimation produces an estimator with several optimal properties, but a convex approach has an obvious advantage in optimization. We demonstrate that in the low-dimensional setting, both estimators are consistent and asymptotically normal, where the asymptotic variance of the non-convex estimator is smaller than the convex counterpart. We also quantify the efficiency gap which provides insight into when the two methods are comparable. In the high-dimensional setting, we show that both estimation procedures achieve $\ell_2$-consistency at the minimax optimal $\sqrt{s\log p/n}$ rates under mild conditions. Finally, we propose an inference procedure using a de-biasing approach. We validate our theoretical findings through simulations and a real-data example.
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes
http://jmlr.org/papers/v21/19-827.html
2020Nathan Kallus, Masatoshi Uehara
Off-policy evaluation (OPE) in reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. We consider for the first time the semiparametric efficiency limits of OPE in Markov decision processes (MDPs), where actions, rewards, and states are memoryless. We show existing OPE estimators may fail to be efficient in this setting. We develop a new estimator based on cross-fold estimation of $q$-functions and marginalized density ratios, which we term double reinforcement learning (DRL). We show that DRL is efficient when both components are estimated at fourth-root rates and is also doubly robust when only one component is consistent. We investigate these properties empirically and demonstrate the performance benefits due to harnessing memorylessness.
High Dimensional Forecasting via Interpretable Vector Autoregression
http://jmlr.org/papers/v21/19-777.html
2020William B. Nicholson, Ines Wilms, Jacob Bien, David S. Matteson
Vector autoregression (VAR) is a fundamental tool for modeling multivariate time series. However, as the number of component series is increased, the VAR model becomes overparameterized. Several authors have addressed this issue by incorporating regularized approaches, such as the lasso in VAR estimation. Traditional approaches address overparameterization by selecting a low lag order, based on the assumption of short range dependence, assuming that a universal lag order applies to all components. Such an approach constrains the relationship between the components and impedes forecast performance. The lasso-based approaches perform much better in high-dimensional situations but do not incorporate the notion of lag order selection. We propose a new class of hierarchical lag structures (HLag) that embed the notion of lag selection into a convex regularizer. The key modeling tool is a group lasso with nested groups which guarantees that the sparsity pattern of lag coefficients honors the VAR's ordered structure. The proposed HLag framework offers three basic structures, which allow for varying levels of flexibility, with many possible generalizations. A simulation study demonstrates improved performance in forecasting and lag order selection over previous approaches, and macroeconomic, financial, and energy applications further highlight forecasting improvements as well as HLag's convenient, interpretable output.
Complete Dictionary Learning via L4-Norm Maximization over the Orthogonal Group
http://jmlr.org/papers/v21/19-755.html
2020Yuexiang Zhai, Zitong Yang, Zhenyu Liao, John Wright, Yi Ma
This paper considers the fundamental problem of learning a complete (orthogonal) dictionary from samples of sparsely generated signals. Most existing methods solve the dictionary (and sparse representations) based on heuristic algorithms, usually without theoretical guarantees for either optimality or complexity. The recent $\ell^1$-minimization based methods do provide such guarantees but the associated algorithms recover the dictionary one column at a time. In this work, we propose a new formulation that maximizes the $\ell^4$-norm over the orthogonal group, to learn the entire dictionary. We prove that under a random data model, with nearly minimum sample complexity, the global optima of the $\ell^4$-norm are very close to signed permutations of the ground truth. Inspired by this observation, we give a conceptually simple and yet effective algorithm based on matching, stretching, and projection (MSP). The algorithm provably converges locally and cost per iteration is merely an SVD. In addition to strong theoretical guarantees, experiments show that the new algorithm is significantly more efficient and effective than existing methods, including KSVD and $\ell^1$-based methods. Preliminary experimental results on mixed real imagery data clearly demonstrate advantages of so learned dictionary over classic PCA bases.
Cramer-Wold Auto-Encoder
http://jmlr.org/papers/v21/19-560.html
2020Szymon Knop, Przemysław Spurek, Jacek Tabor, Igor Podolak, Marcin Mazur, Stanisław Jastrzębski
The computation of the distance to the true distribution is a key component of most state-of-the-art generative models. Inspired by prior works on the Sliced-Wasserstein Auto-Encoders (SWAE) and the Wasserstein Auto-Encoders with MMD-based penalty (WAE-MMD), we propose a new generative model - a Cramer-Wold Auto-Encoder (CWAE). A fundamental component of CWAE is the characteristic kernel, the construction of which is one of the goals of this paper, from here on referred to as the Cramer-Wold kernel. Its main distinguishing feature is that it has a closed-form of the kernel product of radial Gaussians. Consequently, CWAE model has a~closed-form for the distance between the posterior and the normal prior, which simplifies the optimization procedure by removing the need to sample in order to compute the loss function. At the same time, CWAE performance often improves upon WAE-MMD and SWAE on standard benchmarks.
Trust-Region Variational Inference with Gaussian Mixture Models
http://jmlr.org/papers/v21/19-524.html
2020Oleg Arenz, Mingjun Zhong, Gerhard Neumann
Many methods for machine learning rely on approximate inference from intractable probability distributions. Variational inference approximates such distributions by tractable models that can be subsequently used for approximate inference. Learning sufficiently accurate approximations requires a rich model family and careful exploration of the relevant modes of the target distribution. We propose a method for learning accurate GMM approximations of intractable probability distributions based on insights from policy search by using information-geometric trust regions for principled exploration. For efficient improvement of the GMM approximation, we derive a lower bound on the corresponding optimization objective enabling us to update the components independently. Our use of the lower bound ensures convergence to a stationary point of the original objective. The number of components is adapted online by adding new components in promising regions and by deleting components with negligible weight. We demonstrate on several domains that we can learn approximations of complex, multimodal distributions with a quality that is unmet by previous variational inference methods, and that the GMM approximation can be used for drawing samples that are on par with samples created by state-of-the-art MCMC samplers while requiring up to three orders of magnitude less computational resources.
Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information
http://jmlr.org/papers/v21/19-505.html
2020Yichong Xu, Sivaraman Balakrishnan, Aarti Singh, Artur Dubrawski
In supervised learning, we typically leverage a fully labeled dataset to design methods for function estimation or prediction. In many practical situations, we are able to obtain alternative feedback, possibly at a low cost. A broad goal is to understand the usefulness of, and to design algorithms to exploit, this alternative feedback. In this paper, we consider a semi-supervised regression setting, where we obtain additional ordinal (or comparison) information for the unlabeled samples. We consider ordinal feedback of varying qualities where we have either a perfect ordering of the samples, a noisy ordering of the samples or noisy pairwise comparisons between the samples. We provide a precise quantification of the usefulness of these types of ordinal feedback in both nonparametric and linear regression, showing that in many cases it is possible to accurately estimate an underlying function with a very small labeled set, effectively escaping the curse of dimensionality. We also present lower bounds, that establish fundamental limits for the task and show that our algorithms are optimal in a variety of settings. Finally, we present extensive experiments on new datasets that demonstrate the efficacy and practicality of our algorithms and investigate their robustness to various sources of noise and model misspecification.
apricot: Submodular selection for data summarization in Python
http://jmlr.org/papers/v21/19-467.html
2020Jacob Schreiber, Jeffrey Bilmes, William Stafford Noble
We present apricot, an open source Python package for selecting representative subsets from large data sets using submodular optimization. The package implements several efficient greedy selection algorithms that offer strong theoretical guarantees on the quality of the selected set. Additionally, several submodular set functions are implemented, including facility location, which is broadly applicable but requires memory quadratic in the number of examples in the data set, and a feature-based function that is less broadly applicable but can scale to millions of examples. Apricot is extremely efficient, using both algorithmic speedups such as the lazy greedy algorithm and memoization as well as code optimization using numba. We demonstrate the use of subset selection by training machine learning models to comparable accuracy using either the full data set or a representative subset thereof. This paper presents an explanation of submodular selection, an overview of the features in apricot, and applications to two data sets.
Generative Adversarial Nets for Robust Scatter Estimation: A Proper Scoring Rule Perspective
http://jmlr.org/papers/v21/19-462.html
2020Chao Gao, Yuan Yao, Weizhi Zhu
Robust covariance matrix estimation is a fundamental task in statistics. The recent discovery on the connection between robust estimation and generative adversarial nets (GANs) suggests that it is possible to compute depth-like robust estimators using similar techniques that optimize GANs. In this paper, we introduce a general learning via classification framework based on the notion of proper scoring rules. This framework allows us to understand both matrix depth function, a technique of rate-optimal robust estimation, and various GANs through the lens of variational approximations of $f$-divergences induced by proper scoring rules. We then propose a new class of robust covariance matrix estimators in this framework by carefully constructing discriminators with appropriate neural network structures. These estimators are proved to achieve the minimax rate of covariance matrix estimation under Huber's contamination model. The results are also extended to robust scatter estimation for elliptical distributions. Our numerical results demonstrate the good performance of the proposed procedures under various settings against competitors in the literature.
Generating Weighted MAX-2-SAT Instances with Frustrated Loops: an RBM Case Study
http://jmlr.org/papers/v21/19-368.html
2020Yan Ru Pei, Haik Manukian, Massimiliano Di Ventra
Many optimization problems can be cast into the maximum satisfiability (MAX-SAT) form, and many solvers have been developed for tackling such problems. To evaluate a MAXSAT solver, it is convenient to generate hard MAX-SAT instances with known solutions. Here, we propose a method of generating weighted MAX-2-SAT instances inspired by the frustrated-loop algorithm used by the quantum annealing community. We extend the algorithm for instances of general bipartite couplings, with the associated optimization problem being the minimization of the restricted Boltzmann machine (RBM) energy over the nodal values, which is useful for effectively pre-training the RBM. The hardness of the generated instances can be tuned through a central parameter known as the frustration index. Two versions of the algorithm are presented: the random- and structured-loop algorithms. For the random-loop algorithm, we provide a thorough theoretical and empirical analysis on its mathematical properties from the perspective of frustration, and observe empirically a double phase transition behavior in the hardness scaling behavior driven by the frustration index. For the structured-loop algorithm, we show that it offers an improvement in hardness over the random-loop algorithm in the regime of high loop density, with the variation of hardness tunable through the concentration of frustrated weights.
Learning Big Gaussian Bayesian Networks: Partition, Estimation and Fusion
http://jmlr.org/papers/v21/19-318.html
2020Jiaying Gu, Qing Zhou
Structure learning of Bayesian networks has always been a challenging problem. Nowadays, massive-size networks with thousands or more of nodes but fewer samples frequently appear in many areas. We develop a divide-and-conquer framework, called partition-estimation-fusion (PEF), for structure learning of such big networks. The proposed method first partitions nodes into clusters, then learns a subgraph on each cluster of nodes, and finally fuses all learned subgraphs into one Bayesian network. The PEF method is designed in a flexible way so that any structure learning method may be used in the second step to learn a subgraph structure as either a DAG or a CPDAG. In the clustering step, we adapt hierarchical clustering to automatically choose a proper number of clusters. In the fusion step, we propose a novel hybrid method that sequentially adds edges between subgraphs. Extensive numerical experiments demonstrate the competitive performance of our PEF method, in terms of both speed and accuracy compared to existing methods. Our method can improve the accuracy of structure learning by 20% or more, while reducing running time up to two orders-of-magnitude.
Streamlined Variational Inference with Higher Level Random Effects
http://jmlr.org/papers/v21/19-222.html
2020Tui H. Nolan, Marianne Menictas, Matt P. Wand
We derive and present explicit algorithms to facilitate streamlined computing for variational inference for models containing higher level random effects. Existing literature is such that streamlined variational inference is restricted to mean field variational Bayes algorithms for two-level random effects models. Here we provide the following extensions: (1) explicit Gaussian response mean field variational Bayes algorithms for three-level models, (2) explicit algorithms for the alternative variational message passing approach in the case of two-level and three-level models, and (3) an explanation of how arbitrarily high levels of nesting can be handled based on the recently published matrix algebraic results of the authors. A pay-off from (2) is simple extension to non-Gaussian response models. In summary, we remove barriers for streamlining variational inference algorithms based on either the mean field variational Bayes approach or the variational message passing approach when higher level random effects are present.
Asymptotic Consistency of $\alpha$-{R}\'enyi-Approximate Posteriors
http://jmlr.org/papers/v21/19-161.html
2020Prateek Jaiswal, Vinayak Rao, Harsha Honnappa
We study the asymptotic consistency properties of $\alpha$-{R}\'enyi approximate posteriors, a class of variational Bayesian methods that approximate an intractable Bayesian posterior with a member of a tractable family of distributions, the member chosen to minimize the $\alpha$-{R}\'enyi divergence from the true posterior. Unique to our work is that we consider settings with $\alpha > 1$, resulting in approximations that upperbound the log-likelihood, and consequently have wider spread than traditional variational approaches that minimize the Kullback-Liebler (KL) divergence from the posterior. Our primary result identifies sufficient conditions under which consistency holds, centering around the existence of a `good' sequence of distributions in the approximating family that possesses, among other properties, the right rate of convergence to a limit distribution. We further characterize the good sequence by demonstrating that a sequence of distributions that converges too quickly cannot be a good sequence. We also extend our analysis to the setting where $\alpha$ equals one, corresponding to the minimizer of the reverse KL divergence, and to models with local latent variables. We also illustrate the existence of a good sequence with a number of examples. Our results complement a growing body of work focused on the frequentist properties of variational Bayesian methods.
Estimate Sequences for Stochastic Composite Optimization: Variance Reduction, Acceleration, and Robustness to Noise
http://jmlr.org/papers/v21/19-073.html
2020Andrei Kulunchakov, Julien Mairal
In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov. More precisely, we interpret a large class of stochastic optimization methods as procedures that iteratively minimize a surrogate of the objective, which covers the stochastic gradient descent method and variants of the incremental approaches SAGA, SVRG, and MISO/Finito/SDCA. This point of view has several advantages: (i) we provide a simple generic proof of convergence for all of the aforementioned methods; (ii) we naturally obtain new algorithms with the same guarantees; (iii) we derive generic strategies to make these algorithms robust to stochastic noise, which is useful when data is corrupted by small random perturbations. Finally, we propose a new accelerated stochastic gradient descent algorithm and a new accelerated SVRG algorithm that is robust to stochastic noise.
Learning from Binary Multiway Data: Probabilistic Tensor Decomposition and its Statistical Optimality
http://jmlr.org/papers/v21/18-766.html
2020Miaoyan Wang, Lexin Li
We consider the problem of decomposing a higher-order tensor with binary entries. Such data problems arise frequently in applications such as neuroimaging, recommendation system, topic modeling, and sensor network localization. We propose a multilinear Bernoulli model, develop a rank-constrained likelihood-based estimation method, and obtain the theoretical accuracy guarantees. In contrast to continuous-valued problems, the binary tensor problem exhibits an interesting phase transition phenomenon according to the signal-to-noise ratio. The error bound for the parameter tensor estimation is established, and we show that the obtained rate is minimax optimal under the considered model. Furthermore, we develop an alternating optimization algorithm with convergence guarantees. The efficacy of our approach is demonstrated through both simulations and analyses of multiple data sets on the tasks of tensor completion and clustering.
Spectral Algorithms for Community Detection in Directed Networks
http://jmlr.org/papers/v21/18-581.html
2020Zhe Wang, Yingbin Liang, Pengsheng Ji
Community detection in large social networks is affected by degree heterogeneity of nodes. The D-SCORE algorithm for directed networks was introduced to reduce this effect by taking the element-wise ratios of the singular vectors of the adjacency matrix before clustering. Meaningful results were obtained for the statistician citation network, but rigorous analysis on its performance was missing. First, this paper establishes theoretical guarantee for this algorithm and its variants for the directed degree-corrected block model (Directed-DCBM). Second, this paper provides significant improvements for the original D-SCORE algorithms by attaching the nodes outside of the community cores using the information of the original network instead of the singular vectors.
Dual Iterative Hard Thresholding
http://jmlr.org/papers/v21/18-487.html
2020Xiao-Tong Yuan, Bo Liu, Lezi Wang, Qingshan Liu, Dimitris N. Metaxas
Iterative Hard Thresholding (IHT) is a popular class of first-order greedy selection methods for loss minimization under cardinality constraint. The existing IHT-style algorithms, however, are proposed for minimizing the primal formulation. It is still an open issue to explore duality theory and algorithms for such a non-convex and NP-hard combinatorial optimization problem. To address this issue, we develop in this article a novel duality theory for $\ell_2$-regularized empirical risk minimization under cardinality constraint, along with an IHT-style algorithm for dual optimization. Our sparse duality theory establishes a set of sufficient and/or necessary conditions under which the original non-convex problem can be equivalently or approximately solved in a concave dual formulation. In view of this theory, we propose the Dual IHT (DIHT) algorithm as a super-gradient ascent method to solve the non-smooth dual problem with provable guarantees on primal-dual gap convergence and sparsity recovery. Numerical results confirm our theoretical predictions and demonstrate the superiority of DIHT to the state-of-the-art primal IHT-style algorithms in model estimation accuracy and computational efficiency.
Robust Reinforcement Learning with Bayesian Optimisation and Quadrature
http://jmlr.org/papers/v21/18-216.html
2020Supratik Paul, Konstantinos Chatzilygeroudis, Kamil Ciosek, Jean-Baptiste Mouret, Michael A. Osborne, Shimon Whiteson
Bayesian optimisation has been successfully applied to a variety of reinforcement learning problems. However, the traditional approach for learning optimal policies in simulators does not utilise the opportunity to improve learning by adjusting certain environment variables: state features that are unobservable and randomly determined by the environment in a physical setting but are controllable in a simulator. This article considers the problem of finding a robust policy while taking into account the impact of environment variables. We present Alternating Optimisation and Quadrature (ALOQ), which uses Bayesian optimisation and Bayesian quadrature to address such settings. We also present Transferable ALOQ (TALOQ), for settings where simulator inaccuracies lead to difficulty in transferring the learnt policy to the physical system. We show that our algorithms are robust to the presence of significant rare events, which may not be observable under random sampling but play a substantial role in determining the optimal policy. Experimental results across different domains show that our algorithms learn robust policies efficiently.
The Kalai-Smorodinsky solution for many-objective Bayesian optimization
http://jmlr.org/papers/v21/18-212.html
2020Mickael Binois, Victor Picheny, Patrick Taillandier, Abderrahmane Habbal
An ongoing aim of research in multiobjective Bayesian optimization is to extend its applicability to a large number of objectives. While coping with a limited budget of evaluations, recovering the set of optimal compromise solutions generally requires numerous observations and is less interpretable since this set tends to grow larger with the number of objectives. We thus propose to focus on a specific solution originating from game theory, the Kalai-Smorodinsky solution, which possesses attractive properties. In particular, it ensures equal marginal gains over all objectives. We further make it insensitive to a monotonic transformation of the objectives by considering the objectives in the copula space. A novel tailored algorithm is proposed to search for the solution, in the form of a Bayesian optimization algorithm: sequential sampling decisions are made based on acquisition functions that derive from an instrumental Gaussian process prior. Our approach is tested on four problems with respectively four, six, eight, and nine objectives. The method is available in the R package GPGame.
Distributionally Ambiguous Optimization for Batch Bayesian Optimization
http://jmlr.org/papers/v21/18-211.html
2020Nikitas Rontsis, Michael A. Osborne, Paul J. Goulart
We propose a novel, theoretically-grounded, acquisition function for Batch Bayesian Optimization informed by insights from distributionally ambiguous optimization. Our acquisition function is a lower bound on the well-known Expected Improvement function, which requires evaluation of a Gaussian expectation over a multivariate piecewise affine function. Our bound is computed instead by evaluating the best-case expectation over all probability distributions consistent with the same mean and variance as the original Gaussian distribution. Unlike alternative approaches, including Expected Improvement, our proposed acquisition function avoids multi-dimensional integrations entirely, and can be computed exactly - even on large batch sizes - as the solution of a tractable convex optimization problem. Our suggested acquisition function can also be optimized efficiently, since first and second derivative information can be calculated inexpensively as by-products of the acquisition function calculation itself. We derive various novel theorems that ground our work theoretically and we demonstrate superior performance via simple motivating examples, benchmark functions and real-world problems.
Local Causal Network Learning for Finding Pairs of Total and Direct Effects
http://jmlr.org/papers/v21/18-083.html
2020Yue Liu, Zhuangyan Fang, Yangbo He, Zhi Geng, Chunchen Liu
In observational studies, it is important to evaluate not only the total effect but also the direct and indirect effects of a treatment variable on a response variable. In terms of local structural learning of causal networks, we try to find all possible pairs of total and direct causal effects, which can further be used to calculate indirect causal effects. An intuitive global learning approach is first to find an essential graph over all variables representing all Markov equivalent causal networks, and then enumerate all equivalent networks and estimate a pair of the total and direct effects for each of them. However, it could be inefficient to learn an essential graph and enumerate equivalent networks when the true causal graph is large. In this paper, we propose a local learning approach instead. In the local learning approach, we first learn locally a chain component containing the treatment. Then, if necessary, we learn locally a chain component containing the response. Next, we locally enumerate all possible pairs of the treatment's parents and the response's parents. Finally based on these pairs, we find all possible pairs of total and direct effects of the treatment on the response.
Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms
http://jmlr.org/papers/v21/18-041.html
2020Junhong Lin, Volkan Cevher
We study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We first investigate distributed stochastic gradient methods (SGM), with mini-batches and multi-passes over the data. We show that optimal generalization error bounds (up to logarithmic factor) can be retained for distributed SGM provided that the partition level is not too large. We then extend our results to spectral algorithms (SA), including kernel ridge regression (KRR), kernel principal component regression, and gradient methods. Our results show that distributed SGM has a smaller theoretical computational complexity, compared with distributed KRR and classic SGM. Moreover, even for a general non-distributed SA, they provide optimal, capacity-dependent convergence rates, for the case that the regression function may not be in the RKHS in the well-conditioned regimes.
New Insights and Perspectives on the Natural Gradient Method
http://jmlr.org/papers/v21/17-678.html
2020James Martens
Natural gradient descent is an optimization method traditionally motivated from the perspective of information geometry, and works well for many applications as an alternative to stochastic gradient descent. In this paper we critically analyze this method and its properties, and show how it can be viewed as a type of 2nd-order optimization method, with the Fisher information matrix acting as a substitute for the Hessian. In many important cases, the Fisher information matrix is shown to be equivalent to the Generalized Gauss-Newton matrix, which both approximates the Hessian, but also has certain properties that favor its use over the Hessian. This perspective turns out to have significant implications for the design of a practical and robust natural gradient optimizer, as it motivates the use of techniques like trust regions and Tikhonov regularization. Additionally, we make a series of contributions to the understanding of natural gradient and 2nd-order methods, including: a thorough analysis of the convergence speed of stochastic natural gradient descent (and more general stochastic 2nd-order methods) as applied to convex quadratics, a critical examination of the oft-used 'empirical' approximation of the Fisher matrix, and an analysis of the (approximate) parameterization invariance property possessed by natural gradient methods (which we show also holds for certain other curvature matrices, but notably not the Hessian).
Orlicz Random Fourier Features
http://jmlr.org/papers/v21/19-1031.html
2020Linda Chamakh, Emmanuel Gobet, Zoltán Szabó
Kernel techniques are among the most widely-applied and influential tools in machine learning with applications at virtually all areas of the field. To combine this expressive power with computational efficiency numerous randomized schemes have been proposed in the literature, among which probably random Fourier features (RFF) are the simplest and most popular. While RFFs were originally designed for the approximation of kernel values, recently they have been adapted to kernel derivatives, and hence to the solution of large-scale tasks involving function derivatives. Unfortunately, the understanding of the RFF scheme for the approximation of higher-order kernel derivatives is quite limited due to the challenging polynomial growing nature of the underlying function class in the empirical process. To tackle this difficulty, we establish a finite-sample deviation bound for a general class of polynomial-growth functions under $\alpha$-exponential Orlicz condition on the distribution of the sample. Instantiating this result for RFFs, our finite-sample uniform guarantee implies a.s. convergence with tight rate for arbitrary kernel with $\alpha$-exponential Orlicz spectrum and any order of derivative.
Empirical Priors for Prediction in Sparse High-dimensional Linear Regression
http://jmlr.org/papers/v21/19-152.html
2020Ryan Martin, Yiqi Tang
In this paper we adopt the familiar sparse, high-dimensional linear regression model and focus on the important but often overlooked task of prediction. In particular, we consider a new empirical Bayes framework that incorporates data in the prior in two ways: one is to center the prior for the non-zero regression coefficients and the other is to provide some additional regularization. We show that, in certain settings, the asymptotic concentration of the proposed empirical Bayes posterior predictive distribution is very fast, and we establish a Bernstein--von Mises theorem which ensures that the derived empirical Bayes prediction intervals achieve the targeted frequentist coverage probability. The empirical prior has a convenient conjugate form, so posterior computations are relatively simple and fast. Finally, our numerical results demonstrate the proposed method's strong finite-sample performance in terms of prediction accuracy, uncertainty quantification, and computation time compared to existing Bayesian methods.
A Data Efficient and Feasible Level Set Method for Stochastic Convex Optimization with Expectation Constraints
http://jmlr.org/papers/v21/19-1022.html
2020Qihang Lin, Selvaprabu Nadarajah, Negar Soheili, Tianbao Yang
Stochastic convex optimization problems with expectation constraints (SOECs) are encountered in statistics and machine learning, business, and engineering. The SOEC objective and constraints contain expectations defined with respect to complex distributions or large data sets, leading to high computational complexity when solved by the algorithms that use exact functions and their gradients. Recent stochastic first order methods exhibit low computational complexity when handling SOECs but guarantee near-feasibility and near-optimality only at convergence. These methods may thus return highly infeasible solutions when heuristically terminated, as is often the case, due to theoretical convergence criteria being highly conservative. This issue limits the use of first order methods in several applications where the SOEC constraints encode implementation requirements. We design a stochastic feasible level set method (SFLS) for SOECs that has low complexity and emphasizes feasibility before convergence. Specifically, our level-set method solves a root-finding problem by calling a novel first order oracle that computes a stochastic upper bound on the level-set function by extending mirror descent and online validation techniques. We establish that SFLS maintains a high-probability feasible solution at each root-finding iteration and exhibits favorable complexity compared to state-of-the-art deterministic feasible level set and stochastic subgradient methods. Numerical experiments on three diverse applications highlight how SFLS finds feasible solutions with small optimality gaps with lower complexity than the former approaches.
Nesterov's Acceleration for Approximate Newton
http://jmlr.org/papers/v21/19-265.html
2020Haishan Ye, Luo Luo, Zhihua Zhang
Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted considerable attention because of their low computational cost in each iteration. However, these methods might suffer from poor performance when the Hessian is hard to be approximate well in a computation-efficient way. To overcome this dilemma, we resort to Nesterov's acceleration to improve the convergence performance of these second-order methods and propose accelerated approximate Newton. We give the theoretical convergence analysis of accelerated approximate Newton and show that Nesterov's acceleration can improve the convergence rate. Accordingly, we propose an accelerated regularized sub-sampled Newton (ARSSN) which performs much better than the conventional regularized sub-sampled Newton empirically and theoretically. Moreover, we show that ARSSN has better performance than classical first-order methods empirically.
Importance Sampling Techniques for Policy Optimization
http://jmlr.org/papers/v21/20-124.html
2020Alberto Maria Metelli, Matteo Papini, Nico Montali, Marcello Restelli
How can we effectively exploit the collected samples when solving a continuous control task with Reinforcement Learning? Recent results have empirically demonstrated that multiple policy optimization steps can be performed with the same batch by using off-distribution techniques based on importance sampling. However, when dealing with off-distribution optimization, it is essential to take into account the uncertainty introduced by the importance sampling process. In this paper, we propose and analyze a class of model-free, policy search algorithms that extend the recent Policy Optimization via Importance Sampling (Metelli et al., 2018) by incorporating two advanced variance reduction techniques: per-decision and multiple importance sampling. For both of them, we derive a high-probability bound, of independent interest, and then we show how to employ it to define a suitable surrogate objective function that can be used for both action-based and parameter-based settings. The resulting algorithms are finally evaluated on a set of continuous control tasks, using both linear and deep policies, and compared with modern policy optimization methods.
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
http://jmlr.org/papers/v21/20-074.html
2020Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new “Colossal Clean Crawled Corpus”, we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.
Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Networks
http://jmlr.org/papers/v21/19-794.html
2020Amir R. Asadi, Emmanuel Abbe
We derive generalization and excess risk bounds for neural networks using a family of complexity measures based on a multilevel relative entropy. The bounds are obtained by introducing the notion of generated hierarchical coverings of neural networks and by using the technique of chaining mutual information introduced by Asadi et al. '18. The resulting bounds are algorithm-dependent and multiscale: they exploit the multilevel structure of neural networks. This, in turn, leads to an empirical risk minimization problem with a multilevel entropic regularization. The minimization problem is resolved by introducing a multiscale extension of the celebrated Gibbs posterior distribution, proving that the derived distribution achieves the unique minimum. This leads to a new training procedure for neural networks with performance guarantees, which exploits the chain rule of relative entropy rather than the chain rule of derivatives (as in backpropagation), and which takes into account the interactions between different scales of the hypothesis sets of neural networks corresponding to different depths of the hidden layers. To obtain an efficient implementation of the latter, we further develop a multilevel Metropolis algorithm simulating the multiscale Gibbs distribution, with an experiment for a two-layer neural network on the MNIST data set.
metric-learn: Metric Learning Algorithms in Python
http://jmlr.org/papers/v21/19-678.html
2020William de Vazelhes, CJ Carey, Yuan Tang, Nathalie Vauquier, Aurélien Bellet
metric-learn is an open source Python package implementing supervised and weakly-supervised distance metric learning algorithms. As part of scikit-learn-contrib, it provides a unified interface compatible with scikit-learn which allows to easily perform cross-validation, model selection, and pipelining with other machine learning estimators. metric-learn is thoroughly tested and available on PyPi under the MIT license.
Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting
http://jmlr.org/papers/v21/19-650.html
2020Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins, Chicheng Zhang
We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions, while the other requires standard Lipschitz assumptions. Both bounds exhibit data-dependent “zooming” behavior and, with no tuning, yield improved guarantees for benign problems. We also study adapting to unknown smoothness parameters, establishing a price-of-adaptivity and deriving optimal adaptive algorithms that require no additional information.
Convergence Rates for the Stochastic Gradient Descent Method for Non-Convex Objective Functions
http://jmlr.org/papers/v21/19-636.html
2020Benjamin Fehrman, Benjamin Gess, Arnulf Jentzen
We prove the convergence to minima and estimates on the rate of convergence for the stochastic gradient descent method in the case of not necessarily locally convex nor contracting objective functions. In particular, the analysis relies on a quantitative use of mini-batches to control the loss of iterates to non-attracted regions. The applicability of the results to simple objective functions arising in machine learning is shown.
A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks
http://jmlr.org/papers/v21/19-562.html
2020Owen Marschall, Kyunghyun Cho, Cristina Savin
We present a framework for compactly summarizing many recent results in efficient and/or biologically plausible online training of recurrent neural networks (RNN). The framework organizes algorithms according to several criteria: (a) past vs. future facing, (b) tensor structure, (c) stochastic vs. deterministic, and (d) closed form vs. numerical. These axes reveal latent conceptual connections among several recent advances in online learning. Furthermore, we provide novel mathematical intuitions for their degree of success. Testing these algorithms on two parametric task families shows that performances cluster according to our criteria. Although a similar clustering is also observed for pairwise gradient alignment, alignment with exact methods does not explain ultimate performance. This suggests the need for better comparison metrics.
Probabilistic Learning on Graphs via Contextual Architectures
http://jmlr.org/papers/v21/19-470.html
2020Davide Bacciu, Federico Errica, Alessio Micheli
We propose a novel methodology for representation learning on graph-structured data, in which a stack of Bayesian Networks learns different distributions of a vertex's neighbourhood. Through an incremental construction policy and layer-wise training, we can build deeper architectures with respect to typical graph convolutional neural networks, with benefits in terms of context spreading between vertices. First, the model learns from graphs via maximum likelihood estimation without using target labels. Then, a supervised readout is applied to the learned graph embeddings to deal with graph classification and vertex classification tasks, showing competitive results against neural models for graphs. The computational complexity is linear in the number of edges, facilitating learning on large scale data sets. By studying how depth affects the performances of our model, we discover that a broader context generally improves performances. In turn, this leads to a critical analysis of some benchmarks used in literature.
Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers
http://jmlr.org/papers/v21/19-359.html
2020Yao Ma, Alex Olshevsky, Csaba Szepesvari, Venkatesh Saligrama
We consider worker skill estimation for the single-coin Dawid-Skene crowdsourcing model. In practice, skill-estimation is challenging because worker assignments are sparse and irregular due to the arbitrary and uncontrolled availability of workers. We formulate skill estimation as a rank-one correlation-matrix completion problem, where the observed components correspond to observed label correlation between workers. We show that the correlation matrix can be successfully recovered and skills are identifiable if and only if the sampling matrix (observed components) does not have a bipartite connected component. We then propose a projected gradient descent scheme and show that skill estimates converge to the desired global optima for such sampling matrices. Our proof is original and the results are surprising in light of the fact that even the weighted rank-one matrix factorization problem is NP-hard in general. Next, we derive sample complexity bounds in terms of spectral properties of the signless Laplacian of the sampling matrix. Our proposed scheme achieves state-of-art performance on a number of real-world datasets.
Monte Carlo Gradient Estimation in Machine Learning
http://jmlr.org/papers/v21/19-346.html
2020Shakir Mohamed, Mihaela Rosca, Michael Figurnov, Andriy Mnih
This paper is a broad and accessible survey of the methods we have at our disposal for Monte Carlo gradient estimation in machine learning and across the statistical sciences: the problem of computing the gradient of an expectation of a function with respect to parameters defining the distribution that is integrated; the problem of sensitivity analysis. In machine learning research, this gradient problem lies at the core of many learning problems, in supervised, unsupervised and reinforcement learning. We will generally seek to rewrite such gradients in a form that allows for Monte Carlo estimation, allowing them to be easily and efficiently used and analysed. We explore three strategies---the pathwise, score function, and measure-valued gradient estimators---exploring their historical development, derivation, and underlying assumptions. We describe their use in other fields, show how they are related and can be combined, and expand on their possible generalisations. Wherever Monte Carlo gradient estimators have been derived and deployed in the past, important advances have followed. A deeper and more widely-held understanding of this problem will lead to further advances, and it is these advances that we wish to support.
Convergence of Sparse Variational Inference in Gaussian Processes Regression
http://jmlr.org/papers/v21/19-1015.html
2020David R. Burt, Carl Edward Rasmussen, Mark van der Wilk
Gaussian processes are distributions over functions that are versatile and mathematically convenient priors in Bayesian modelling. However, their use is often impeded for data with large numbers of observations, $N$, due to the cubic (in $N$) cost of matrix operations used in exact inference. Many solutions have been proposed that rely on $M \ll N$ inducing variables to form an approximation at a cost of $\mathcal{O}\left(NM^2\right)$. While the computational cost appears linear in $N$, the true complexity depends on how $M$ must scale with $N$ to ensure a certain quality of the approximation. In this work, we investigate upper and lower bounds on how $M$ needs to grow with $N$ to ensure high quality approximations. We show that we can make the KL-divergence between the approximate model and the exact posterior arbitrarily small for a Gaussian-noise regression model with $M \ll N$. Specifically, for the popular squared exponential kernel and $D$-dimensional Gaussian distributed covariates, $M = \mathcal{O}((\log N)^D)$ suffice and a method with an overall computational cost of $\mathcal{O}\left(N(\log N)^{2D}(\log \log N)^2\right)$ can be used to perform inference.
AI Explainability 360: An Extensible Toolkit for Understanding Data and Machine Learning Models
http://jmlr.org/papers/v21/19-1035.html
2020Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilović, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John T. Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang
As artificial intelligence algorithms make further inroads in high-stakes societal applications, there are increasing calls from multiple stakeholders for these algorithms to explain their outputs. To make matters more challenging, different personas of consumers of explanations have different requirements for explanations. Toward addressing these needs, we introduce AI Explainability 360, an open-source Python toolkit featuring ten diverse and state-of-the-art explainability methods and two evaluation metrics. Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of interpretation and explanation methods, not only those in the toolkit but also in the broader literature on explainability. For data scientists and other users of the toolkit, we have implemented an extensible software architecture that organizes methods according to their place in the AI modeling pipeline. The toolkit is not only the software, but also guidance material, tutorials, and an interactive web demo to introduce AI explainability to different audiences. Together, our toolkit and taxonomy can help identify gaps where more explainability methods are needed and provide a platform to incorporate them as they are developed.
A General System of Differential Equations to Model First-Order Adaptive Algorithms
http://jmlr.org/papers/v21/18-808.html
2020Andre Belotto da Silva, Maxime Gazeau
First-order optimization algorithms play a major role in large scale machine learning. A new class of methods, called adaptive algorithms, was recently introduced to adjust iteratively the learning rate for each coordinate. Despite great practical success in deep learning, their behavior and performance on more general loss functions are not well understood. In this paper, we derive a non-autonomous system of differential equations, which is the continuous-time limit of adaptive optimization methods. We study the convergence of its trajectories and give conditions under which the differential system, underlying all adaptive algorithms, is suitable for optimization. We discuss convergence to a critical point in the non-convex case and give conditions for the dynamics to avoid saddle points and local maxima. For convex loss function, we introduce a suitable Lyapunov functional which allows us to study its rate of convergence. Several other properties of both the continuous and discrete systems are briefly discussed. The differential system studied in the paper is general enough to encompass many other classical algorithms (such as Heavy Ball and Nesterov's accelerated method) and allow us to recover several known results for these algorithms.
A Regularization-Based Adaptive Test for High-Dimensional GLMs
http://jmlr.org/papers/v21/18-807.html
2020Chong Wu, Gongjun Xu, Xiaotong Shen, Wei Pan
In spite of its urgent importance in the era of big data, testing high-dimensional parameters in generalized linear models (GLMs) in the presence of high-dimensional nuisance parameters has been largely under-studied, especially with regard to constructing powerful tests for general (and unknown) alternatives. Most existing tests are powerful only against certain alternatives and may yield incorrect Type 1 error rates under high-dimensional nuisance parameter situations. In this paper, we propose the adaptive interaction sum of powered score (aiSPU) test in the framework of penalized regression with a non-convex penalty, called truncated Lasso penalty (TLP), which can maintain correct Type 1 error rates while yielding high statistical power across a wide range of alternatives. To calculate its p-values analytically, we derive its asymptotic null distribution. Via simulations, its superior finite-sample performance is demonstrated over several representative existing methods. In addition, we apply it and other representative tests to an Alzheimer's Disease Neuroimaging Initiative (ADNI) data set, detecting possible gene-gender interactions for Alzheimer's disease. We also put R package “aispu” implementing the proposed test on GitHub.
Apache Mahout: Machine Learning on Distributed Dataflow Systems
http://jmlr.org/papers/v21/18-800.html
2020Robin Anil, Gokhan Capan, Isabel Drost-Fromm, Ted Dunning, Ellen Friedman, Trevor Grant, Shannon Quinn, Paritosh Ranjan, Sebastian Schelter, Özgür Yılmazel
Apache Mahout is a library for scalable machine learning (ML) on distributed dataflow systems, offering various implementations of classification, clustering, dimensionality reduction and recommendation algorithms. Mahout was a pioneer in large-scale machine learning in 2008, when it started and targeted MapReduce, which was the predominant abstraction for scalable computing in industry at that time. Mahout has been widely used by leading web companies and is part of several commercial cloud offerings. In recent years, Mahout migrated to a general framework enabling a mix of dataflow programming and linear algebraic computations on backends such as Apache Spark and Apache Flink. This design allows users to execute data preprocessing and model training in a single, unified dataflow system, instead of requiring a complex integration of several specialized systems. Mahout is maintained as a community-driven open source project at the Apache Software Foundation, and is available under https://mahout.apache.org.
Distributed Minimum Error Entropy Algorithms
http://jmlr.org/papers/v21/18-696.html
2020Xin Guo, Ting Hu, Qiang Wu
Minimum Error Entropy (MEE) principle is an important approach in Information Theoretical Learning (ITL). It is widely applied and studied in various fields for its robustness to noise. In this paper, we study a reproducing kernel-based distributed MEE algorithm, DMEE, which is designed to work with both fully supervised data and semi-supervised data. The divide-and-conquer approach is employed, so there is no inter-node communication overhead. Similar as other distributed algorithms, DMEE significantly reduces the computational complexity and memory requirement on single computing nodes. With fully supervised data, our proved learning rates equal the minimax optimal learning rates of the classical pointwise kernel-based regressions. Under the semi-supervised learning scenarios, we show that DMEE exploits unlabeled data effectively, in the sense that first, under the settings with weak regularity assumptions, additional unlabeled data significantly improves the learning rates of DMEE. Second, with sufficient unlabeled data, labeled data can be distributed to many more computing nodes, that each node takes only O(1) labels, without spoiling the learning rates in terms of the number of labels. This conclusion overcomes the saturation phenomenon in unlabeled data size. It parallels a recent results for regularized least squares (Lin and Zhou, 2018), and suggests that an inflation of unlabeled data is a solution to the MEE learning problems with decentralized data source for the concerns of privacy protection. Our work refers to pairwise learning and non-convex loss. The theoretical analysis is achieved by distributed U-statistics and error decomposition techniques in integral operators.
Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular Maximization
http://jmlr.org/papers/v21/18-527.html
2020Rad Niazadeh, Tim Roughgarden, Joshua R. Wang
In this paper we study the fundamental problems of maximizing a continuous non-monotone submodular function over the hypercube, both with and without coordinate-wise concavity. This family of optimization problems has several applications in machine learning, economics, and communication systems. Our main result is the first $\frac{1}{2}$-approximation algorithm for continuous submodular function maximization; this approximation factor of $\frac{1}{2}$ is the best possible for algorithms that only query the objective function at polynomially many points. For the special case of DR-submodular maximization, i.e. when the submodular function is also coordinate-wise concave along all coordinates, we provide a different $\frac{1}{2}$-approximation algorithm that runs in quasi-linear time. Both these results improve upon prior work (Bian et al. 2017; Soma and Yoshida, 2017). Our first algorithm uses novel ideas such as reducing the guaranteed approximation problem to analyzing a zero-sum game for each coordinate, and incorporates the geometry of this zero-sum game to fix the value at this coordinate. Our second algorithm exploits coordinate-wise concavity to identify a monotone equilibrium condition sufficient for getting the required approximation guarantee, and hunts for the equilibrium point using binary search. We further run experiments to verify the performance of our proposed algorithms in related machine learning applications.
Fast Bayesian Inference of Sparse Networks with Automatic Sparsity Determination
http://jmlr.org/papers/v21/18-514.html
2020Hang Yu, Songwei Wu, Luyin Xin, Justin Dauwels
Structure learning of Gaussian graphical models typically involves careful tuning of penalty parameters, which balance the tradeoff between data fidelity and graph sparsity. Unfortunately, this tuning is often a “black art” requiring expert experience or brute-force search. It is therefore tempting to develop tuning-free algorithms that can determine the sparsity of the graph adaptively from the observed data in an automatic fashion. In this paper, we propose a novel approach, named BISN (Bayesian inference of Sparse Networks), for automatic Gaussian graphical model selection. Specifically, we regard the off-diagonal entries in the precision matrix as random variables and impose sparse-promoting horseshoe priors on them, resulting in automatic sparsity determination. With the help of stochastic gradients, an efficient variational Bayes algorithm is derived to learn the model. We further propose a decaying recursive stochastic gradient (DRSG) method to reduce the variance of the stochastic gradients and to accelerate the convergence. Our theoretical analysis shows that the time complexity of BISN scales only quadratically with the dimension, whereas the theoretical time complexity of the state-of-the-art methods for automatic graphical model selection is typically a third-order function of the dimension. Furthermore, numerical results show that BISN can achieve comparable or better performance than the state-of-the-art methods in terms of structure recovery, and yet its computational time is several orders of magnitude shorter, especially for large dimensions.
Tensor Regression Networks
http://jmlr.org/papers/v21/18-503.html
2020Jean Kossaifi, Zachary C. Lipton, Arinbjorn Kolbeinsson, Aran Khanna, Tommaso Furlanello, Anima Anandkumar
Convolutional neural networks typically consist of many convolutional layers followed by one or more fully connected layers. While convolutional layers map between high-order activation tensors, the fully connected layers operate on flattened activation vectors. Despite empirical success, this approach has notable drawbacks. Flattening followed by fully connected layers discards multilinear structure in the activations and requires many parameters. We address these problems by incorporating tensor algebraic operations that preserve multilinear structure at every layer. First, we introduce Tensor Contraction Layers (TCLs) that reduce the dimensionality of their input while preserving their multilinear structure using tensor contraction. Next, we introduce Tensor Regression Layers (TRLs), which express outputs through a low-rank multilinear mapping from a high-order activation tensor to an output tensor of arbitrary order. We learn the contraction and regression factors end-to-end, and produce accurate nets with fewer parameters. Additionally, our layers regularize networks by imposing low-rank constraints on the activations (TCL) and regression weights (TRL). Experiments on ImageNet show that, applied to VGG and ResNet architectures, TCLs and TRLs reduce the number of parameters compared to fully connected layers by more than 65% while maintaining or increasing accuracy. In addition to the space savings, our approach's ability to leverage topological structure can be crucial for structured data such as MRI. In particular, we demonstrate significant performance improvements over comparable architectures on three tasks associated with the UK Biobank dataset.
Kernel-estimated Nonparametric Overlap-Based Syncytial Clustering
http://jmlr.org/papers/v21/18-435.html
2020Israel A. Almodóvar-Rivera, Ranjan Maitra
Commonly-used clustering algorithms usually find ellipsoidal, spherical or other regular-structured clusters, but are more challenged when the underlying groups lack formal structure or definition. Syncytial clustering is the name that we introduce for methods that merge groups obtained from standard clustering algorithms in order to reveal complex group structure in the data. Here, we develop a distribution-free fully-automated syncytial clustering algorithm that can be used with $k$-means and other algorithms. Our approach estimates the cumulative distribution function of the normed residuals from an appropriately fit $k$-groups model and calculates the estimated nonparametric overlap between each pair of clusters. Groups with high pairwise overlap are merged as long as the estimated generalized overlap decreases. Our methodology is always a top performer in identifying groups with regular and irregular structures in several datasets and can be applied to datasets with scatter or incomplete records. The approach is also used to identify the distinct kinds of gamma ray bursts in the Burst and Transient Source Experiment 4Br catalog and the distinct kinds of activation in a functional Magnetic Resonance Imaging study.
Agnostic Estimation for Phase Retrieval
http://jmlr.org/papers/v21/18-259.html
2020Matey Neykov, Zhaoran Wang, Han Liu
The goal of noisy high-dimensional phase retrieval is to estimate an $s$-sparse parameter $\boldsymbol{\beta}^*\in \mathbb{R}^d$ from $n$ realizations of the model $Y = (\mathbf{X}^T \boldsymbol{\beta}^*)^2 + \varepsilon$. Based on this model, we propose a significant semi-parametric generalization called misspecified phase retrieval (MPR), in which $Y = f(\mathbf{X}^T \boldsymbol{\beta}^*, \varepsilon)$ with unknown $f$ and $\operatorname{Cov}(Y, (\mathbf{X}^T \boldsymbol{\beta}^*)^2) > 0$. For example, MPR encompasses $Y = h(|\mathbf{X}^T \boldsymbol{\beta}^*|) + \varepsilon$ with increasing $h$ as a special case. Despite the generality of the MPR model, it eludes the reach of most existing semi-parametric estimators. In this paper, we propose an estimation procedure, which consists of solving a cascade of two convex programs and provably recovers the direction of $\boldsymbol{\beta}^*$. Furthermore, we prove that our procedure is minimax optimal over the class of MPR models. Interestingly, our minimax analysis characterizes the statistical price of misspecifying the link function in phase retrieval models. Our theory is backed up by thorough numerical results.
A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning
http://jmlr.org/papers/v21/16-311.html
2020Aryan Mokhtari, Alec Koppel, Martin Takac, Alejandro Ribeiro
We consider learning problems over training sets in which both, the number of training examples and the dimension of the feature vectors, are large. To solve these problems we propose the random parallel stochastic algorithm (RAPSA). We call the algorithm random parallel because it utilizes multiple parallel processors to operate on a randomly chosen subset of blocks of the feature vector. RAPSA is doubly stochastic since each processor utilizes a random set of functions to compute the stochastic gradient associated with a randomly chosen sets of variable coordinates. Algorithms that are parallel in either of these dimensions exist, but RAPSA is the first attempt at a methodology that is parallel in both the selection of blocks and the selection of elements of the training set. In RAPSA, processors utilize the randomly chosen functions to compute the stochastic gradient component associated with a randomly chosen block. The technical contribution of this paper is to show that this minimally coordinated algorithm converges to the optimal classifier when the training objective is strongly convex. Moreover, we present an accelerated version of RAPSA (ARAPSA) that incorporates the objective function curvature information by premultiplying the descent direction by a Hessian approximation matrix. We further extend the results for asynchronous settings and show that if the processors perform their updates without any coordination the algorithms are still convergent to the optimal argument. RAPSA and its extensions are then numerically evaluated on a linear estimation problem and a binary image classification task using the MNIST handwritten digit dataset.
Bayesian Closed Surface Fitting Through Tensor Products
http://jmlr.org/papers/v21/13-233.html
2020Olivier Binette, Debdeep Pati, David B. Dunson
Closed surfaces provide a useful model for $3$-d shapes, with the data typically consisting of a cloud of points in $\mathbb{R}^3$. The existing literature on closed surface modeling focuses on frequentist point estimation methods that join surface patches along the edges, with surface patches created via Bézier surfaces or tensor products of B-splines. However, the resulting surfaces are not smooth along the edges and the geometric constraints required to join the surface patches lead to computational drawbacks. In this article, we develop a Bayesian model for closed surfaces based on tensor products of a cyclic basis resulting in infinitely smooth surface realizations. We impose sparsity on the control points through a double-shrinkage prior. Theoretical properties of the support of our proposed prior are studied and it is shown that the posterior achieves the optimal rate of convergence under reasonable assumptions on the prior. The proposed approach is illustrated with some examples.
Tslearn, A Machine Learning Toolkit for Time Series Data
http://jmlr.org/papers/v21/20-091.html
2020Romain Tavenard, Johann Faouzi, Gilles Vandewiele, Felix Divo, Guillaume Androz, Chester Holtz, Marie Payne, Roman Yurchak, Marc Rußwurm, Kushal Kolar, Eli Woods
tslearn is a general-purpose Python machine learning library for time series that offers tools for pre-processing and feature extraction as well as dedicated models for clustering, classification and regression. It follows scikit-learn's Application Programming Interface for transformers and estimators, allowing the use of standard pipelines and model selection tools on top of tslearn objects. It is distributed under the BSD-2-Clause license, and its source code is available at https://github.com/tslearn-team/tslearn.
Regularized Estimation of High-dimensional Factor-Augmented Vector Autoregressive (FAVAR) Models
http://jmlr.org/papers/v21/19-874.html
2020Jiahe Lin, George Michailidis
A factor-augmented vector autoregressive (FAVAR) model is defined by a VAR equation that captures lead-lag correlations amongst a set of observed variables $X$ and latent factors $F$, and a calibration equation that relates another set of observed variables $Y$ with $F$ and $X$. The latter equation is used to estimate the factors that are subsequently used in estimating the parameters of the VAR system. The FAVAR model has become popular in applied economic research, since it can summarize a large number of variables of interest as a few factors through the calibration equation and subsequently examine their influence on core variables of primary interest through the VAR equation. However, there is increasing need for examining lead-lag relationships between a large number of time series, while incorporating information from another high-dimensional set of variables. Hence, in this paper we investigate the FAVAR model under high-dimensional scaling. We introduce an appropriate identification constraint for the model parameters, which when incorporated into the formulated optimization problem yields estimates with good statistical properties. Further, we address a number of technical challenges introduced by the fact that estimates of the VAR system model parameters are based on estimated rather than directly observed quantities. The performance of the proposed estimators is evaluated on synthetic data. Further, the model is applied to commodity prices and reveals interesting and interpretable relationships between the prices and the factors extracted from a set of global macroeconomic indicators.
GluonTS: Probabilistic and Neural Time Series Modeling in Python
http://jmlr.org/papers/v21/19-820.html
2020Alexander Alexandrov, Konstantinos Benidis, Michael Bohlke-Schneider, Valentin Flunkert, Jan Gasthaus, Tim Januschowski, Danielle C. Maddix, Syama Rangapuram, David Salinas, Jasper Schulz, Lorenzo Stella, Ali Caner Türkmen, Yuyang Wang
We introduce the Gluon Time Series Toolkit (GluonTS), a Python library for deep learning based time series modeling for ubiquitous tasks, such as forecasting and anomaly detection. GluonTS simplifies the time series modeling pipeline by providing the necessary components and tools for quick model development, efficient experimentation and evaluation. In addition, it contains reference implementations of state-of-the-art time series models that enable simple benchmarking of new algorithms.
Identifiability and Consistent Estimation of Nonparametric Translation Hidden Markov Models with General State Space
http://jmlr.org/papers/v21/19-802.html
2020Elisabeth Gassiat, Sylvain Le Corff, Luc Lehéricy
This paper considers hidden Markov models where the observations are given as the sum of a latent state which lies in a general state space and some independent noise with unknown distribution. It is shown that these fully nonparametric translation models are identifiable with respect to both the distribution of the latent variables and the distribution of the noise, under mostly a light tail assumption on the latent variables. Two nonparametric estimation methods are proposed and we prove that the corresponding estimators are consistent for the weak convergence topology. These results are illustrated with numerical experiments.
NEVAE: A Deep Generative Model for Molecular Graphs
http://jmlr.org/papers/v21/19-671.html
2020Bidisha Samanta, Abir De, Gourhari Jana, Vicenç Gómez, Pratim Chattaraj, Niloy Ganguly, Manuel Gomez-Rodriguez
Deep generative models have been praised for their ability to learn smooth latent representations of images, text, and audio, which can then be used to generate new, plausible data. Motivated by these success stories, there has been a surge of interest in developing deep generative models for automated molecule design. However, these models face several difficulties due to the unique characteristics of molecular graphs—their underlying structure is not Euclidean or grid-like, they remain isomorphic under permutation of the nodes’ labels, and they come with a different number of nodes and edges. In this paper, we first propose a novel variational autoencoder for molecular graphs, whose encoder and decoder are specially designed to account for the above properties by means of several technical innovations. Moreover, in contrast with the state of the art, our decoder is able to provide the spatial coordinates of the atoms of the molecules it generates. Then, we develop a gradient-based algorithm to optimize the decoder of our model so that it learns to generate molecules that maximize the value of certain property of interest and, given any arbitrary molecule, it is able to optimize the spatial configuration of its atoms for greater stability. Experiments reveal that our variational autoencoder can discover plausible, diverse and novel molecules more effectively than several state of the art models. Moreover, for several properties of interest, our optimized decoder is able to identify molecules with property values 121% higher than those identified by several state of the art methods based on Bayesian optimization and reinforcement learning.
Prediction regions through Inverse Regression
http://jmlr.org/papers/v21/19-535.html
2020Emilie Devijver, Emeline Perthame
Predicting a new response from a covariate is a challenging task in regression, which raises new question since the era of high-dimensional data. In this paper, we are interested in the inverse regression method from a theoretical viewpoint. Theoretical results for the well-known Gaussian linear model are well-known, but the curse of dimensionality has increased the interest of practitioners and theoreticians into generalization of those results for various estimators, calibrated for the high-dimension context. We propose to focus on inverse regression. It is known to be a reliable and efficient approach when the number of features exceeds the number of observations. Indeed, under some conditions, dealing with the inverse regression problem associated to a forward regression problem drastically reduces the number of parameters to estimate, makes the problem tractable and allows to consider more general distributions, as elliptical distributions. When both the responses and the covariates are multivariate, estimators constructed by the inverse regression are studied in this paper, the main result being explicit asymptotic prediction regions for the response. The performances of the proposed estimators and prediction regions are also analyzed through a simulation study and compared with usual estimators.
High-dimensional Linear Discriminant Analysis Classifier for Spiked Covariance Model
http://jmlr.org/papers/v21/19-428.html
2020Houssem Sifaou, Abla Kammoun, Mohamed-Slim Alouini
Linear discriminant analysis (LDA) is a popular classifier that is built on the assumption of common population covariance matrix across classes. The performance of LDA depends heavily on the quality of estimating the mean vectors and the population covariance matrix. This issue becomes more challenging in high-dimensional settings where the number of features is of the same order as the number of training samples. Several techniques for estimating the covariance matrix can be found in the literature. One of the most popular approaches are estimators based on using a regularized sample covariance matrix, giving the name regularized LDA (R-LDA) to the corresponding classifier. These estimators are known to be more resilient to the sample noise than the traditional sample covariance matrix estimator. However, the main challenge of the regularization approach is the choice of the optimal regularization parameter, as an arbitrary choice could lead to severe degradation of the classifier performance. In this work, we propose an improved LDA classifier based on the assumption that the covariance matrix follows a spiked covariance model. The main principle of our proposed technique is the design of a parametrized inverse covariance matrix estimator, the parameters of which are shown to be easily optimized. Numerical simulations, using both real and synthetic data, show that the proposed classifier yields better classification performance than the classical R-LDA while requiring lower computational complexity.
MFE: Towards reproducible meta-feature extraction
http://jmlr.org/papers/v21/19-348.html
2020Edesio Alcobaça, Felipe Siqueira, Adriano Rivolli, Luís P. F. Garcia, Jefferson T. Oliva, André C. P. L. F. de Carvalho
Automated recommendation of machine learning algorithms is receiving a large deal of attention, not only because they can recommend the most suitable algorithms for a new task, but also because they can support efficient hyper-parameter tuning, leading to better machine learning solutions. The automated recommendation can be implemented using meta-learning, learning from previous learning experiences, to create a meta-model able to associate a data set to the predictive performance of machine learning algorithms. Although a large number of publications report the use of meta-learning, reproduction and comparison of meta-learning experiments is a difficult task. The literature lacks extensive and comprehensive public tools that enable the reproducible investigation of the different meta-learning approaches. An alternative to deal with this difficulty is to develop a meta-feature extractor package with the main characterization measures, following uniform guidelines that facilitate the use and inclusion of new meta-features. In this paper, we propose two Meta-Feature Extractor (MFE) packages, written in both Python and R, to fill this lack. The packages follow recent frameworks for meta-feature extraction, aiming to facilitate the reproducibility of meta-learning experiments.
ProxSARAH: An Efficient Algorithmic Framework for Stochastic Composite Nonconvex Optimization
http://jmlr.org/papers/v21/19-248.html
2020Nhan H. Pham, Lam M. Nguyen, Dzung T. Phan, Quoc Tran-Dinh
We propose a new stochastic first-order algorithmic framework to solve stochastic composite nonconvex optimization problems that covers both finite-sum and expectation settings. Our algorithms rely on the SARAH estimator and consist of two steps: a proximal gradient and an averaging step making them different from existing nonconvex proximal-type algorithms. The algorithms only require an average smoothness assumption of the nonconvex objective term and additional bounded variance assumption if applied to expectation problems. They work with both constant and dynamic step-sizes, while allowing single sample and mini-batches. In all these cases, we prove that our algorithms can achieve the best-known complexity bounds in terms of stochastic first-order oracle. One key step of our methods is the new constant and dynamic step-sizes resulting in the desired complexity bounds while improving practical performance. Our constant step-size is much larger than existing methods including proximal SVRG scheme in the single sample case. We also specify our framework to the non-composite case that covers existing state-of-the-arts in terms of oracle complexity bounds. Our update also allows one to trade-off between step-sizes and mini-batch sizes to improve performance. We test the proposed algorithms on two composite nonconvex problems and neural networks using several well-known data sets.
Bayesian Model Selection with Graph Structured Sparsity
http://jmlr.org/papers/v21/19-123.html
2020Youngseok Kim, Chao Gao
We propose a general algorithmic framework for Bayesian model selection. A spike-and-slab Laplacian prior is introduced to model the underlying structural assumption. Using the notion of effective resistance, we derive an EM-type algorithm with closed-form iterations to efficiently explore possible candidates for Bayesian model selection. The deterministic nature of the proposed algorithm makes it more scalable to large-scale and high-dimensional data sets compared with existing stochastic search algorithms. When applied to sparse linear regression, our framework recovers the EMVS algorithm by Ročková and George (2014) as a special case. We also discuss extensions of our framework using tools from graph algebra to incorporate complex Bayesian models such as biclustering and submatrix localization. Extensive simulation studies and real data applications are conducted to demonstrate the superior performance of our methods over its frequentist competitors such as $\ell_0$ or $\ell_1$ penalization.
ThunderGBM: Fast GBDTs and Random Forests on GPUs
http://jmlr.org/papers/v21/19-095.html
2020Zeyi Wen, Hanfeng Liu, Jiashuai Shi, Qinbin Li, Bingsheng He, Jian Chen
Gradient Boosting Decision Trees (GBDTs) and Random Forests (RFs) have been used in many real-world applications. They are often a standard recipe for building state-of-the-art solutions to machine learning and data mining problems. However, training and prediction are very expensive computationally for large and high dimensional problems. This article presents an efficient and open source software toolkit called ThunderGBM which exploits the high-performance Graphics Processing Units (GPUs) for GBDTs and RFs. ThunderGBM supports classification, regression and ranking, and can run on single or multiple GPUs of a machine. Our experimental results show that ThunderGBM outperforms the existing libraries while producing similar models, and can handle high dimensional problems where existing GPU-based libraries fail. Documentation, examples, and more details about ThunderGBM are available at https://github.com/xtra-computing/thundergbm.
Change Point Estimation in a Dynamic Stochastic Block Model
http://jmlr.org/papers/v21/18-814.html
2020Monika Bhattacharjee, Moulinath Banerjee, George Michailidis
We consider the problem of estimating the location of a single change point in a network generated by a dynamic stochastic block model mechanism. This model produces community structure in the network that exhibits change at a single time epoch. We propose two methods of estimating the change point, together with the model parameters, before and after its occurrence. The first employs a least-squares criterion function and takes into consideration the full structure of the stochastic block model and is evaluated at each point in time. Hence, as an intermediate step, it requires estimating the community structure based on a clustering algorithm at every time point. The second method comprises the following two steps: in the first one, a least-squares function is used and evaluated at each time point, but ignoring the community structure and only considering a random graph generating mechanism exhibiting a change point. Once the change point is identified, in the second step, all network data before and after it are used together with a clustering algorithm to obtain the corresponding community structures and subsequently estimate the generating stochastic block model parameters. The first method, since it requires knowledge of the community structure and hence clustering at every point in time, is significantly more computationally expensive than the second one. On the other hand, it requires a significantly less stringent identifiability condition for consistent estimation of the change point and the model parameters than the second method; however, it also requires a condition on the misclassification rate of misallocating network nodes to their respective communities that may fail to hold in many realistic settings. Despite the apparent stringency of the identifiability condition for the second method, we show that networks generated by a stochastic block mechanism exhibiting a change in their structure can easily satisfy this condition under a multitude of scenarios, including merging/splitting communities, nodes joining another community, etc. Further, for both methods under their respective identifiability and certain additional regularity conditions, we establish rates of convergence and derive the asymptotic distributions of the change point estimators. The results are illustrated on synthetic data. In summary, this work provides an in-depth investigation of the novel problem of change point analysis for networks generated by stochastic block models, identifies key conditions for the consistent estimation of the change point, and proposes a computationally fast algorithm that solves the problem in many settings that occur in applications. Finally, it discusses challenges posed by employing clustering algorithms in this problem, that require additional investigation for their full resolution.
Quadratic Decomposable Submodular Function Minimization: Theory and Practice
http://jmlr.org/papers/v21/18-790.html
2020Pan Li, Niao He, Olgica Milenkovic
We introduce a new convex optimization problem, termed quadratic decomposable submodular function minimization (QDSFM), which allows to model a number of learning tasks on graphs and hypergraphs. The problem exhibits close ties to decomposable submodular function minimization (DSFM) yet is much more challenging to solve. We approach the problem via a new dual strategy and formulate an objective that can be optimized through a number of double-loop algorithms. The outer-loop uses either random coordinate descent (RCD) or alternative projection (AP) methods, for both of which we prove linear convergence rates. The inner-loop computes projections onto cones generated by base polytopes of the submodular functions via the modified min-norm-point or Frank-Wolfe algorithms. We also describe two new applications of QDSFM: hypergraph-adapted PageRank and semi-supervised learning. The proposed hypergraph-based PageRank algorithm can be used for local hypergraph partitioning and comes with provable performance guarantees. For hypergraph-adapted semi-supervised learning, we provide numerical experiments demonstrating the efficiency of our QDSFM solvers and their significant improvements on prediction accuracy when compared to state-of-the-art methods.
Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization
http://jmlr.org/papers/v21/18-764.html
2020Aryan Mokhtari, Hamed Hassani, Amin Karbasi
This paper considers stochastic optimization problems for a large class of objective functions, including convex and continuous submodular. Stochastic proximal gradient methods have been widely used to solve such problems; however, their applicability remains limited when the problem dimension is large and the projection onto a convex set is computationally costly. Instead, stochastic conditional gradient algorithms are proposed as an alternative solution which rely on (i) Approximating gradients via a simple averaging technique requiring a single stochastic gradient evaluation per iteration; (ii) Solving a linear program to compute the descent/ascent direction. The gradient averaging technique reduces the noise of gradient approximations as time progresses, and replacing projection step in proximal methods by a linear program lowers the computational complexity of each iteration. We show that under convexity and smoothness assumptions, our proposed stochastic conditional gradient method converges to the optimal objective function value at a sublinear rate of $\mathcal{O}(1/t^{1/3})$. Further, for a monotone and continuous DR-submodular function and subject to a general convex body constraint, we prove that our proposed method achieves a $((1-1/e)\text{OPT} -\epsilon)$ guarantee (in expectation) with $\mathcal{O}{(1/\epsilon^3)}$ stochastic gradient computations. This guarantee matches the known hardness results and closes the gap between deterministic and stochastic continuous submodular maximization. Additionally, we achieve $((1/e)\text{OPT} -\epsilon)$ guarantee after operating on $\mathcal{O}{(1/\epsilon^3)}$ stochastic gradients for the case that the objective function is continuous DR-submodular but non-monotone and the constraint set is a down-closed convex body. By using stochastic continuous optimization as an interface, we also provide the first $(1-1/e)$ tight approximation guarantee for maximizing a monotone but stochastic submodular set function subject to a general matroid constraint and $(1/e)$ approximation guarantee for the non-monotone case.
Sparse Projection Oblique Randomer Forests
http://jmlr.org/papers/v21/18-664.html
2020Tyler M. Tomita, James Browne, Cencheng Shen, Jaewon Chung, Jesse L. Patsolic, Benjamin Falk, Carey E. Priebe, Jason Yim, Randal Burns, Mauro Maggioni, Joshua T. Vogelstein
Decision forests, including Random Forests and Gradient Boosting Trees, have recently demonstrated state-of-the-art performance in a variety of machine learning settings. Decision forests are typically ensembles of axis-aligned decision trees; that is, trees that split only along feature dimensions. In contrast, many recent extensions to decision forests are based on axis-oblique splits. Unfortunately, these extensions forfeit one or more of the favorable properties of decision forests based on axis-aligned splits, such as robustness to many noise dimensions, interpretability, or computational efficiency. We introduce yet another decision forest, called “Sparse Projection Oblique Randomer Forests” (SPORF). SPORF trees recursively split along very sparse random projections. Our method significantly improves accuracy over existing state-of-the-art algorithms on a standard benchmark suite for classification with $>100$ problems of varying dimension, sample size, and number of classes. To illustrate how SPORF addresses the limitations of both axis-aligned and existing oblique decision forest methods, we conduct extensive simulated experiments. SPORF typically yields improved performance over existing decision forest methods, while mitigating computational efficiency and scalability and maintaining interpretability. Very sparse random projections can be incorporated into gradient boosted trees to obtain potentially similar gains.
Stochastic Nested Variance Reduction for Nonconvex Optimization
http://jmlr.org/papers/v21/18-447.html
2020Dongruo Zhou, Pan Xu, Quanquan Gu
We study nonconvex optimization problems, where the objective function is either an average of $n$ nonconvex functions or the expectation of some stochastic function. We propose a new stochastic gradient descent algorithm based on nested variance reduction, namely, Stochastic Nested Variance-Reduced Gradient descent ($\text{SNVRG}$). Compared with conventional stochastic variance reduced gradient ($\text{SVRG}$) algorithm that uses two reference points to construct a semi-stochastic gradient with diminishing variance in each iteration, our algorithm uses $K+1$ nested reference points to build a semi-stochastic gradient to further reduce its variance in each iteration. For smooth nonconvex functions, $\text{SNVRG}$ converges to an $\epsilon$-approximate first-order stationary point within $\tilde O(n\land\epsilon^{-2}+\epsilon^{-3}\land n^{1/2}\epsilon^{-2})$ number of stochastic gradient evaluations. This improves the best known gradient complexity of $\text{SVRG}$ $O(n+n^{2/3}\epsilon^{-2})$ and that of $\text{SCSG}$ $O(n\land \epsilon^{-2}+\epsilon^{-10/3}\land n^{2/3}\epsilon^{-2})$. For gradient dominated functions, $\text{SNVRG}$ also achieves better gradient complexity than the state-of-the-art algorithms.
Based on $\text{SNVRG}$, we further propose two algorithms that can find local minima faster than state-of-the-art algorithms in both finite-sum and general stochastic (online) nonconvex optimization. In particular, for finite-sum optimization problems, the proposed $\text{SNVRG}+\text{Neon2}^{\text{finite}}$ algorithm achieves $\tilde{O}(n^{1/2}\epsilon^{-2}+n\epsilon_H^{-3}+n^{3/4}\epsilon_H^{-7/2})$ gradient complexity to converge to an $(\epsilon, \epsilon_H)$-second-order stationary point, which outperforms $\text{SVRG}+\text{Neon2}^{\text{finite}}$ (Allen-Zhu and Li, 2018), the best existing algorithm, in a wide regime. For general stochastic optimization problems, the proposed $\text{SNVRG}+\text{Neon2}^{\text{online}}$ achieves $\tilde{O}(\epsilon^{-3}+\epsilon_H^{-5}+\epsilon^{-2}\epsilon_H^{-3})$ gradient complexity, which is better than both $\text{SVRG}+\text{Neon2}^{\text{online}}$ (Allen-Zhu and Li, 2018) and $\text{Natasha2}$ (Allen-Zhu, 2018a) in certain regimes. Thorough experimental results on different nonconvex optimization problems back up our theory.
AI-Toolbox: A C++ library for Reinforcement Learning and Planning (with Python Bindings)
http://jmlr.org/papers/v21/18-402.html
2020Eugenio Bargiacchi, Diederik M. Roijers, Ann Nowé
This paper describes AI-Toolbox, a C++ software library that contains reinforcement learning and planning algorithms, and supports both single and multi agent problems, as well as partial observability. It is designed for simplicity and clarity, and contains extensive documentation of its API and code. It supports Python to enable users not comfortable with C++ to take advantage of the library's speed and functionality. AI-Toolbox is free software, and is hosted online at https://github.com/Svalorzen/AI-Toolbox.
Regularized Gaussian Belief Propagation with Nodes of Arbitrary Size
http://jmlr.org/papers/v21/18-101.html
2020Francois Kamper, Sarel J. Steel, Johan A. du Preez
Gaussian belief propagation (GaBP) is a message-passing algorithm that can be used to perform approximate inference on a pairwise Markov graph (MG) constructed from a multivariate Gaussian distribution in canonical parameterization. The output of GaBP is a set of approximate univariate marginals for each variable in the pairwise MG. An extension of GaBP (labeled GaBP-m), allowing for the approximation of higher-dimensional marginal distributions, was explored by Kamper et al. (2019). The idea is to create an MG in which each node is allowed to receive more than one variable. As in the univariate case, the multivariate extension does not necessarily converge in loopy graphs and, even if convergence occurs, is not guaranteed to provide exact inference. To address the problem of convergence, we consider a multivariate extension of the principle of node regularization proposed by Kamper et al. (2018). We label this algorithm slow GaBP-m (sGaBP-m), where the term 'slow' relates to the damping effect of the regularization on the message passing. We prove that, given sufficient regularization, this algorithm will converge and provide the exact marginal means at convergence, regardless of the way variables are assigned to nodes. The selection of the degree of regularization is addressed through the use of a heuristic, which is based on a tree representation of sGaBP-m. As a further contribution, we extend other GaBP variants in the literature to allow for higher-dimensional marginalization. We show that our algorithm compares favorably with these variants, both in terms of convergence speed and inference quality.
General Latent Feature Models for Heterogeneous Datasets
http://jmlr.org/papers/v21/17-328.html
2020Isabel Valera, Melanie F. Pradier, Maria Lomeli, Zoubin Ghahramani
Latent variable models allow capturing the hidden structure underlying the data. In particular, feature allocation models represent each observation by a linear combination of latent variables. These models are often used to make predictions either for new observations or for missing information in the original data, as well as to perform exploratory data analysis. Although there is an extensive literature on latent feature allocation models for homogeneous datasets, where all the attributes that describe each object are of the same (continuous or discrete) type, there is no general framework for practical latent feature modeling for heterogeneous datasets. In this paper, we introduce a general Bayesian nonparametric latent feature allocation model suitable for heterogeneous datasets, where the attributes describing each object can be arbitrary combinations of real-valued, positive real-valued, categorical, ordinal and count variables. The proposed model presents several important properties. First, it is suitable for heterogeneous data while keeping the properties of conjugate models, which enables us to develop an inference algorithm that presents linear complexity with respect to the number of objects and attributes per MCMC iteration. Second, the Bayesian nonparametric component allows us to place a prior distribution on the number of features required to capture the latent structure in the data. Third, the latent features in the model are binary-valued, which facilitates the interpretability of the obtained latent features in exploratory data analysis. Finally, a software package, called GLFM toolbox, is made publicly available for other researchers to use and extend. It is available at https://ivaleram.github.io/GLFM/. We show the flexibility of the proposed model by solving both prediction and data analysis tasks on several real-world datasets.
Joint Causal Inference from Multiple Contexts
http://jmlr.org/papers/v21/17-123.html
2020Joris M. Mooij, Sara Magliacane, Tom Claassen
The gold standard for discovering causal relations is by means of experimentation. Over the last decades, alternative methods have been proposed that can infer causal relations between variables from certain statistical patterns in purely observational data. We introduce Joint Causal Inference (JCI), a novel approach to causal discovery from multiple data sets from different contexts that elegantly unifies both approaches. JCI is a causal modeling framework rather than a specific algorithm, and it can be implemented using any causal discovery algorithm that can take into account certain background knowledge. JCI can deal with different types of interventions (e.g., perfect, imperfect, stochastic, etc.) in a unified fashion, and does not require knowledge of intervention targets or types in case of interventional data. We explain how several well-known causal discovery algorithms can be seen as addressing special cases of the JCI framework, and we also propose novel implementations that extend existing causal discovery methods for purely observational data to the JCI setting. We evaluate different JCI implementations on synthetic data and on flow cytometry protein expression data and conclude that JCI implementations can considerably outperform state-of-the-art causal discovery algorithms.
A General Framework for Consistent Structured Prediction with Implicit Loss Embeddings
http://jmlr.org/papers/v21/20-097.html
2020Carlo Ciliberto, Lorenzo Rosasco, Alessandro Rudi
We propose and analyze a novel theoretical and algorithmic framework for structured prediction. While so far the term has referred to discrete output spaces, here we consider more general settings, such as manifolds or spaces of probability measures. We define structured prediction as a problem where the output space lacks a vectorial structure. We identify and study a large class of loss functions that implicitly defines a suitable geometry on the problem. The latter is the key to develop an algorithmic framework amenable to a sharp statistical analysis and yielding efficient computations. When dealing with output spaces with infinite cardinality, a suitable implicit formulation of the estimator is shown to be crucial.
Loss Control with Rank-one Covariance Estimate for Short-term Portfolio Optimization
http://jmlr.org/papers/v21/19-959.html
2020Zhao-Rong Lai, Liming Tan, Xiaotian Wu, Liangda Fang
In short-term portfolio optimization (SPO), some financial characteristics like the expected return and the true covariance might be dynamic. Then there are only a small window size $w$ of observations that are sufficiently close to the current moment and reliable to make estimations. $w$ is usually much smaller than the number of assets $d$, which leads to a typical undersampled problem. Worse still, the asset price relatives are not likely subject to any proper distributions. These facts violate the statistical assumptions of the traditional covariance estimates and invalidate their statistical efficiency and consistency in risk measurement. In this paper, we propose to reconsider the function of covariance estimates in the perspective of operators, and establish a rank-one covariance estimate in the principal rank-one tangent space at the observation matrix. Moreover, we propose a loss control scheme with this estimate, which effectively catches the instantaneous risk structure and avoids extreme losses. We conduct extensive experiments on $7$ real-world benchmark daily or monthly data sets with stocks, funds and portfolios from diverse regional markets to show that the proposed method achieves state-of-the-art performance in comprehensive downside risk metrics and gains good investing incomes as well. It offers a novel perspective of rank-related approaches for undersampled estimations in SPO.
pyDML: A Python Library for Distance Metric Learning
http://jmlr.org/papers/v21/19-864.html
2020Juan Luis Suárez, Salvador García, Francisco Herrera
pyDML is an open-source python library that provides a wide range of distance metric learning algorithms. Distance metric learning can be useful to improve similarity learning algorithms, such as the nearest neighbors classifier, and also has other applications, like dimensionality reduction. The pyDML package currently provides more than 20 algorithms, which can be categorized, according to their purpose, in: dimensionality reduction algorithms, algorithms to improve nearest neighbors or nearest centroids classifiers, information theory based algorithms or kernel based algorithms, among others. In addition, the library also provides some utilities for the visualization of classifier regions, parameter tuning and a stats website with the performance of the implemented algorithms. The package relies on the scipy ecosystem, it is fully compatible with scikit-learn, and is distributed under GPLv3 license. Source code and documentation can be found at https://github.com/jlsuarezdiaz/pyDML.
Cornac: A Comparative Framework for Multimodal Recommender Systems
http://jmlr.org/papers/v21/19-805.html
2020Aghiles Salah, Quoc-Tuan Truong, Hady W. Lauw
Cornac is an open-source Python framework for multimodal recommender systems. In addition to core utilities for accessing, building, evaluating, and comparing recommender models, Cornac is distinctive in putting emphasis on recommendation models that leverage auxiliary information in the form of a social network, item textual descriptions, product images, etc. Such multimodal auxiliary data supplement user-item interactions (e.g., ratings, clicks), which tend to be sparse in practice. To facilitate broad adoption and community contribution, Cornac is publicly available at https://github.com/PreferredAI/cornac, and it can be installed via Anaconda or the Python Package Index (pip). Not only is it well-covered by unit tests to ensure code quality, but it is also accompanied with a detailed documentation, tutorials, examples, and several built-in benchmarking data sets.
Minimax Nonparametric Parallelism Test
http://jmlr.org/papers/v21/19-800.html
2020Xin Xing, Meimei Liu, Ping Ma, Wenxuan Zhong
Testing the hypothesis of parallelism is a fundamental statistical problem arising from many applied sciences. In this paper, we develop a nonparametric parallelism test for inferring whether the trends are parallel in treatment and control groups. In particular, the proposed nonparametric parallelism test is a Wald type test based on a smoothing spline ANOVA (SSANOVA) model which can characterize the complex patterns of the data. We derive that the asymptotic null distribution of the test statistic is a Chi-square distribution, unveiling a new version of Wilks phenomenon. Notably, we establish the minimax sharp lower bound of the distinguishable rate for the nonparametric parallelism test by using the information theory, and further prove that the proposed test is minimax optimal. Simulation studies are conducted to investigate the empirical performance of the proposed test. DNA methylation and neuroimaging studies are presented to illustrate potential applications of the test. The software is available at https://github.com/BioAlgs/Parallelism.
Distributed Kernel Ridge Regression with Communications
http://jmlr.org/papers/v21/19-592.html
2020Shao-Bo Lin, Di Wang, Ding-Xuan Zhou
This paper focuses on generalization performance analysis for distributed algorithms in the framework of learning theory. Taking distributed kernel ridge regression (DKRR) for example, we succeed in deriving its optimal learning rates in expectation and providing theoretically optimal ranges of the number of local processors. Due to the gap between theory and experiments, we also deduce optimal learning rates for DKRR in probability to essentially reflect the generalization performance and limitations of DKRR. Furthermore, we propose a communication strategy to improve the learning performance of DKRR and demonstrate the power of communications in DKRR via both theoretical assessments and numerical experiments.
Fast mixing of Metropolized Hamiltonian Monte Carlo: Benefits of multi-step gradients
http://jmlr.org/papers/v21/19-441.html
2020Yuansi Chen, Raaz Dwivedi, Martin J. Wainwright, Bin Yu
Hamiltonian Monte Carlo (HMC) is a state-of-the-art Markov chain Monte Carlo sampling algorithm for drawing samples from smooth probability densities over continuous spaces. We study the variant most widely used in practice, Metropolized HMC with the Stormer-Verlet or leapfrog integrator, and make two primary contributions. First, we provide a non-asymptotic upper bound on the mixing time of the Metropolized HMC with explicit choices of step-size and number of leapfrog steps. This bound gives a precise quantification of the faster convergence of Metropolized HMC relative to simpler MCMC algorithms such as the Metropolized random walk, or Metropolized Langevin algorithm. Second, we provide a general framework for sharpening mixing time bounds of Markov chains initialized at a substantial distance from the target distribution over continuous spaces. We apply this sharpening device to the Metropolized random walk and Langevin algorithms, thereby obtaining improved mixing time bounds from a non-warm initial distribution.
Simultaneous Inference for Pairwise Graphical Models with Generalized Score Matching
http://jmlr.org/papers/v21/19-383.html
2020Ming Yu, Varun Gupta, Mladen Kolar
Probabilistic graphical models provide a flexible yet parsimonious framework for modeling dependencies among nodes in networks. There is a vast literature on parameter estimation and consistent model selection for graphical models. However, in many of the applications, scientists are also interested in quantifying the uncertainty associated with the estimated parameters and selected models, which current literature has not addressed thoroughly. In this paper, we propose a novel estimator for statistical inference on edge parameters in pairwise graphical models based on generalized Hyvarinen scoring rule. Hyvarinen scoring rule is especially useful in cases where the normalizing constant cannot be obtained efficiently in a closed form, which is a common problem for graphical models, including Ising models and truncated Gaussian graphical models. Our estimator allows us to perform statistical inference for general graphical models whereas the existing works mostly focus on statistical inference for Gaussian graphical models where finding normalizing constant is computationally tractable. Under mild conditions that are typically assumed in the literature for consistent estimation, we prove that our proposed estimator is $\sqrt{n}$-consistent and asymptotically normal, which allows us to construct confidence intervals and build hypothesis tests for edge parameters. Moreover, we show how our proposed method can be applied to test hypotheses that involve a large number of model parameters simultaneously. We illustrate validity of our estimator through extensive simulation studies on a diverse collection of data-generating processes.
Probabilistic Symmetries and Invariant Neural Networks
http://jmlr.org/papers/v21/19-322.html
2020Benjamin Bloem-Reddy, Yee Whye Teh
Treating neural network inputs and outputs as random variables, we characterize the structure of neural networks that can be used to model data that are invariant or equivariant under the action of a compact group. Much recent research has been devoted to encoding invariance under symmetry transformations into neural network architectures, in an effort to improve the performance of deep neural networks in data-scarce, non-i.i.d., or unsupervised settings. By considering group invariance from the perspective of probabilistic symmetry, we establish a link between functional and probabilistic symmetry, and obtain generative functional representations of probability distributions that are invariant or equivariant under the action of a compact group. Our representations completely characterize the structure of neural networks that can be used to model such distributions and yield a general program for constructing invariant stochastic or deterministic neural networks. We demonstrate that examples from the recent literature are special cases, and develop the details of the general program for exchangeable sequences and arrays.
Causal Discovery from Heterogeneous/Nonstationary Data
http://jmlr.org/papers/v21/19-232.html
2020Biwei Huang, Kun Zhang, Jiji Zhang, Joseph Ramsey, Ruben Sanchez-Romero, Clark Glymour, Bernhard Schölkopf
It is commonplace to encounter heterogeneous or nonstationary data, of which the underlying generating process changes across domains or over time. Such a distribution shift feature presents both challenges and opportunities for causal discovery. In this paper, we develop a framework for causal discovery from such data, called Constraint-based causal Discovery from heterogeneous/NOnstationary Data (CD-NOD), to find causal skeleton and directions and estimate the properties of mechanism changes. First, we propose an enhanced constraint-based procedure to detect variables whose local mechanisms change and recover the skeleton of the causal structure over observed variables. Second, we present a method to determine causal orientations by making use of independent changes in the data distribution implied by the underlying causal model, benefiting from information carried by changing distributions. After learning the causal structure, next, we investigate how to efficiently estimate the “driving force” of the nonstationarity of a causal mechanism. That is, we aim to extract from data a low-dimensional representation of changes. The proposed methods are nonparametric, with no hard restrictions on data distributions and causal mechanisms, and do not rely on window segmentation. Furthermore, we find that data heterogeneity benefits causal structure identification even with particular types of confounders. Finally, we show the connection between heterogeneity/nonstationarity and soft intervention in causal discovery. Experimental results on various synthetic and real-world data sets (task-fMRI and stock market data) are presented to demonstrate the efficacy of the proposed methods.
Target–Aware Bayesian Inference: How to Beat Optimal Conventional Estimators
http://jmlr.org/papers/v21/19-102.html
2020Tom Rainforth, Adam Golinski, Frank Wood, Sheheryar Zaidi
Standard approaches for Bayesian inference focus solely on approximating the posterior distribution. Typically, this approximation is, in turn, used to calculate expectations for one or more target functions—a computational pipeline that is inefficient when the target function(s) are known upfront. We address this inefficiency by introducing a framework for target–aware Bayesian inference (TABI) that estimates these expectations directly. While conventional Monte Carlo estimators have a fundamental limit on the error they can achieve for a given sample size, our TABI framework is able to breach this limit; it can theoretically produce arbitrarily accurate estimators using only three samples, while we show empirically that it can also breach this limit in practice. We utilize our TABI framework by combining it with adaptive importance sampling approaches and show both theoretically and empirically that the resulting estimators are capable of converging faster than the standard $\mathcal{O}(1/N)$ Monte Carlo rate, potentially producing rates as fast as $\mathcal{O}(1/N^2)$. We further combine our TABI framework with amortized inference methods, to produce a method for amortizing the cost of calculating expectations. Finally, we show how TABI can be used to convert any marginal likelihood estimator into a target aware inference scheme and demonstrate the substantial benefits this can yield.
Constrained Dynamic Programming and Supervised Penalty Learning Algorithms for Peak Detection in Genomic Data
http://jmlr.org/papers/v21/18-843.html
2020Toby Dylan Hocking, Guillem Rigaill, Paul Fearnhead, Guillaume Bourque
Peak detection in genomic data involves segmenting counts of DNA sequence reads aligned to different locations of a chromosome. The goal is to detect peaks with higher counts, and filter out background noise with lower counts. Most existing algorithms for this problem are unsupervised heuristics tailored to patterns in specific data types. We propose a supervised framework for this problem, using optimal changepoint detection models with learned penalty functions. We propose the first dynamic programming algorithm that is guaranteed to compute the optimal solution to changepoint detection problems with constraints between adjacent segment mean parameters. Implementing this algorithm requires the choice of penalty parameter that determines the number of segments that are estimated. We show how the supervised learning ideas of Rigaill et al. (2013) can be used to choose this penalty. We compare the resulting implementation of our algorithm to several baselines in a benchmark of labeled ChIP-seq data sets with two different patterns (broad H3K36me3 data and sharp H3K4me3 data). Whereas baseline unsupervised methods only provide accurate peak detection for a single pattern, our supervised method achieves state-of-the-art accuracy in all data sets. The log-linear timings of our proposed dynamic programming algorithm make it scalable to the large genomic data sets that are now common. Our implementation is available in the PeakSegOptimal R package on CRAN.
Convergence Rate of Optimal Quantization and Application to the Clustering Performance of the Empirical Measure
http://jmlr.org/papers/v21/18-804.html
2020Yating Liu, Gilles Pagès
We study the convergence rate of the optimal quantization for a probability measure sequence $(\mu_{n})_{n\in\mathbb{N}^{*}}$ on $\mathbb{R}^{d}$ converging in the Wasserstein distance in two aspects: the first one is the convergence rate of optimal quantizer $x^{(n)}\in(\mathbb{R}^{d})^{K}$ of $\mu_{n}$ at level $K$; the other one is the convergence rate of the distortion function valued at $x^{(n)}$, called the “performance” of $x^{(n)}$. Moreover, we also study the mean performance of the optimal quantization for the empirical measure of a distribution $\mu$ with finite second moment but possibly unbounded support. As an application, we show an upper bound with a convergence rate $\mathcal{O}(\frac{\log n}{\sqrt{n}})$ of the mean performance for the empirical measure of the multidimensional normal distribution $\mathcal{N}(m, \Sigma)$ and of distributions with hyper-exponential tails. This extends the results from Biau et al. (2008) obtained for compactly supported distribution. We also derive an upper bound which is sharper in the quantization level $K$ but suboptimal in $n$ by applying results in Fournier and Guillin (2015).
Effective Ways to Build and Evaluate Individual Survival Distributions
http://jmlr.org/papers/v21/18-772.html
2020Humza Haider, Bret Hoehn, Sarah Davis, Russell Greiner
An accurate model of a patient’s individual survival distribution can help determine the appropriate treatment for terminal patients. Unfortunately, risk scores (for example from Cox Proportional Hazard models) do not provide survival probabilities, single-time probability models (for instance the Gail model, predicting 5 year probability) only provide for a single time point, and standard Kaplan-Meier survival curves provide only population averages for a large class of patients, meaning they are not specific to individual patients. This motivates an alternative class of tools that can learn a model that provides an individual survival distribution for each subject, which gives survival probabilities across all times, such as extensions to the Cox model, Accelerated Failure Time, an extension to Random Survival Forests, and Multi-Task Logistic Regression. This paper first motivates such 'individual survival distribution' (ISD) models, and explains how they differ from standard models. It then discusses ways to evaluate such models — namely Concordance, 1-Calibration, Integrated Brier score, and versions of L1-loss — then motivates and defines a novel approach, 'D-Calibration', which determines whether a model's probability estimates are meaningful. We also discuss how these measures differ, and use them to evaluate several ISD prediction tools over a range of survival data sets. We also provide a code base for all of these survival models and evaluation measures, at https://github.com/haiderstats/ISDEvaluation.
Model-Preserving Sensitivity Analysis for Families of Gaussian Distributions
http://jmlr.org/papers/v21/18-668.html
2020Christiane Görgen, Manuele Leonelli
The accuracy of probability distributions inferred using machine-learning algorithms heavily depends on data availability and quality. In practical applications it is therefore fundamental to investigate the robustness of a statistical model to misspecification of some of its underlying probabilities. In the context of graphical models, investigations of robustness fall under the notion of sensitivity analyses. These analyses consist in varying some of the model's probabilities or parameters and then assessing how far apart the original and the varied distributions are. However, for Gaussian graphical models, such variations usually make the original graph an incoherent representation of the model's conditional independence structure. Here we develop an approach to sensitivity analysis which guarantees the original graph remains valid after any probability variation and we quantify the effect of such variations using different measures. To achieve this we take advantage of algebraic techniques to both concisely represent conditional independence and to provide a straightforward way of checking the validity of such relationships. Our methods are demonstrated to be robust and comparable to standard ones, which can break the conditional independence structure of the model, using an artificial example and a medical real-world application.
Discerning the Linear Convergence of ADMM for Structured Convex Optimization through the Lens of Variational Analysis
http://jmlr.org/papers/v21/18-562.html
2020Xiaoming Yuan, Shangzhi Zeng, Jin Zhang
Despite the rich literature, the linear convergence of alternating direction method of multipliers (ADMM) has not been fully understood even for the convex case. For example, the linear convergence of ADMM can be empirically observed in a wide range of applications arising in statistics, machine learning, and related areas, while existing theoretical results seem to be too stringent to be satisfied or too ambiguous to be checked and thus why the ADMM performs linear convergence for these applications still seems to be unclear. In this paper, we systematically study the local linear convergence of ADMM in the context of convex optimization through the lens of variational analysis. We show that the local linear convergence of ADMM can be guaranteed without the strong convexity of objective functions together with the full rank assumption of the coefficient matrices, or the full polyhedricity assumption of their subdifferential; and it is possible to discern the local linear convergence for various concrete applications, especially for some representative models arising in statistical learning. We use some variational analysis techniques sophisticatedly; and our analysis is conducted in the most general proximal version of ADMM with Fortin and Glowinski's larger step size so that all major variants of the ADMM known in the literature are covered.
Sequential change-point detection in high-dimensional Gaussian graphical models
http://jmlr.org/papers/v21/18-410.html
2020Hossein Keshavarz, George Michaildiis, Yves Atchade
High dimensional piecewise stationary graphical models represent a versatile class for modelling time varying networks arising in diverse application areas, including biology, economics, and social sciences. There has been recent work in offline detection and estimation of regime changes in the topology of sparse graphical models. However, the online setting remains largely unexplored, despite its high relevance to applications in sensor networks and other engineering monitoring systems, as well as financial markets. To that end, this work introduces a novel scalable online algorithm for detecting an unknown number of abrupt changes in the inverse covariance matrix of sparse Gaussian graphical models with small delay. The proposed algorithm is based upon monitoring the conditional log-likelihood of all nodes in the network and can be extended to a large class of continuous and discrete graphical models. We also investigate asymptotic properties of our procedure under certain mild regularity conditions on the graph size, sparsity level, number of samples, and pre- and post-changes in the topology of the network. Numerical works on both synthetic and real data illustrate the good performance of the proposed methodology both in terms of computational and statistical efficiency across numerous experimental settings.
Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly
http://jmlr.org/papers/v21/18-223.html
2020Kirthevasan Kandasamy, Karun Raju Vysyaraju, Willie Neiswanger, Biswajit Paria, Christopher R. Collins, Jeff Schneider, Barnabas Poczos, Eric P. Xing
Bayesian Optimisation (BO) refers to a suite of techniques for global optimisation of expensive black box functions, which use introspective Bayesian models of the function to efficiently search for the optimum. While BO has been applied successfully in many applications, modern optimisation tasks usher in new challenges where conventional methods fail spectacularly. In this work, we present Dragonfly, an open source Python library for scalable and robust BO. Dragonfly incorporates multiple recently developed methods that allow BO to be applied in challenging real world settings; these include better methods for handling higher dimensional domains, methods for handling multi-fidelity evaluations when cheap approximations of an expensive function are available, methods for optimising over structured combinatorial spaces, such as the space of neural network architectures, and methods for handling parallel evaluations. Additionally, we develop new methodological improvements in BO for selecting the Bayesian model, selecting the acquisition function, and optimising over complex domains with different variable types and additional constraints. We compare Dragonfly to a suite of other packages and algorithms for global optimisation and demonstrate that when the above methods are integrated, they enable significant improvements in the performance of BO. The Dragonfly library is available at dragonfly.github.io.
Memoryless Sequences for General Losses
http://jmlr.org/papers/v21/18-042.html
2020Rafael Frongillo, Andrew Nobel
One way to define the randomness of a fixed individual sequence is to ask how hard it is to predict relative to a given loss function. A sequence is memoryless if, with respect to average loss, no continuous function can predict the next entry of the sequence from a finite window of previous entries better than a constant prediction. For squared loss, memoryless sequences are known to have stochastic attributes analogous to those of truly random sequences. In this paper, we address the question of how changing the loss function changes the set of memoryless sequences, and in particular, the stochastic attributes they possess. For convex differentiable losses we establish that the statistic or property elicited by the loss determines the identity and stochastic attributes of the corresponding memoryless sequences. We generalize these results to convex non-differentiable losses, under additional assumptions, and to non-convex Bregman divergences. In particular, our results show that any Bregman divergence has the same set of memoryless sequences as squared loss. We apply our results to price calibration in prediction markets.
Quantile Graphical Models: a Bayesian Approach
http://jmlr.org/papers/v21/17-231.html
2020Nilabja Guha, Veera Baladandayuthapani, Bani K. Mallick
Graphical models are ubiquitous tools to describe the interdependence between variables measured simultaneously such as large-scale gene or protein expression data. Gaussian graphical models (GGMs) are well-established tools for probabilistic exploration of dependence structures using precision matrices and they are generated under a multivariate normal joint distribution. However, they suffer from several shortcomings since they are based on Gaussian distribution assumptions. In this article, we propose a Bayesian quantile based approach for sparse estimation of graphs. We demonstrate that the resulting graph estimation is robust to outliers and applicable under general distributional assumptions. Furthermore, we develop efficient variational Bayes approximations to scale the methods for large data sets. Our methods are applied to a novel cancer proteomics data dataset where-in multiple proteomic antibodies are simultaneously assessed on tumor samples using reverse-phase protein arrays (RPPA) technology.
Harmless Overfitting: Using Denoising Autoencoders in Estimation of Distribution Algorithms
http://jmlr.org/papers/v21/16-543.html
2020Malte Probst, Franz Rothlauf
Estimation of Distribution Algorithms (EDAs) are metaheuristics where learning a model and sampling new solutions replaces the variation operators recombination and mutation used in standard Genetic Algorithms. The choice of these models as well as the corresponding training processes are subject to the bias/variance tradeoff, also known as under- and overfitting: simple models cannot capture complex interactions between problem variables, whereas complex models are susceptible to modeling random noise. This paper suggests using Denoising Autoencoders (DAEs) as generative models within EDAs (DAE-EDA). The resulting DAE-EDA is able to model complex probability distributions. Furthermore, overfitting is less harmful, since DAEs overfit by learning the identity function. This overfitting behavior introduces unbiased random noise into the samples, which is no major problem for the EDA but just leads to higher population diversity. As a result, DAE-EDA runs for more generations before convergence and searches promising parts of the solution space more thoroughly. We study the performance of DAE-EDA on several combinatorial single-objective optimization problems. In comparison to the Bayesian Optimization Algorithm, DAE-EDA requires a similar number of evaluations of the objective function but is much faster and can be parallelized efficiently, making it the preferred choice especially for large and difficult optimization problems.
Multi-Player Bandits: The Adversarial Case
http://jmlr.org/papers/v21/19-912.html
2020Pragnya Alatur, Kfir Y. Levy, Andreas Krause
We consider a setting where multiple players sequentially choose among a common set of actions (arms). Motivated by an application to cognitive radio networks, we assume that players incur a loss upon colliding, and that communication between players is not possible. Existing approaches assume that the system is stationary. Yet this assumption is often violated in practice, e.g., due to signal strength fluctuations. In this work, we design the first multi-player Bandit algorithm that provably works in arbitrarily changing environments, where the losses of the arms may even be chosen by an adversary. This resolves an open problem posed by Rosenski et al. (2016).
GADMM: Fast and Communication Efficient Framework for Distributed Machine Learning
http://jmlr.org/papers/v21/19-718.html
2020Anis Elgabli, Jihong Park, Amrit S. Bedi, Mehdi Bennis, Vaneet Aggarwal
When the data is distributed across multiple servers, lowering the communication cost between the servers (or workers) while solving the distributed learning problem is an important problem and is the focus of this paper. In particular, we propose a fast, and communication-efficient decentralized framework to solve the distributed machine learning (DML) problem. The proposed algorithm, Group Alternating Direction Method of Multipliers (GADMM) is based on the Alternating Direction Method of Multipliers (ADMM) framework. The key novelty in GADMM is that it solves the problem in a decentralized topology where at most half of the workers are competing for the limited communication resources at any given time. Moreover, each worker exchanges the locally trained model only with two neighboring workers, thereby training a global model with a lower amount of communication overhead in each exchange. We prove that GADMM converges to the optimal solution for convex loss functions, and numerically show that it converges faster and more communication-efficient than the state-of-the-art communication-efficient algorithms such as the Lazily Aggregated Gradient (LAG) and dual averaging, in linear and logistic regression tasks on synthetic and real datasets. Furthermore, we propose Dynamic GADMM (D-GADMM), a variant of GADMM, and prove its convergence under the time-varying network topology of the workers.
Identifiability of Additive Noise Models Using Conditional Variances
http://jmlr.org/papers/v21/19-664.html
2020Gunwoong Park
This paper considers a new identifiability condition for additive noise models (ANMs) in which each variable is determined by an arbitrary Borel measurable function of its parents plus an independent error. It has been shown that ANMs are fully recoverable under some identifiability conditions, such as when all error variances are equal. However, this identifiable condition could be restrictive, and hence, this paper focuses on a relaxed identifiability condition that involves not only error variances, but also the influence of parents. This new class of identifiable ANMs does not put any constraints on the form of dependencies, or distributions of errors, and allows different error variances. It further provides a statistically consistent and computationally feasible structure learning algorithm for the identifiable ANMs based on the new identifiability condition. The proposed algorithm assumes that all relevant variables are observed, while it does not assume faithfulness or a sparse graph. Demonstrated through extensive simulated and real multivariate data is that the proposed algorithm successfully recovers directed acyclic graphs.
High-dimensional Gaussian graphical models on network-linked data
http://jmlr.org/papers/v21/19-563.html
2020Tianxi Li, Cheng Qian, Elizaveta Levina, Ji Zhu
Graphical models are commonly used to represent conditional dependence relationships between variables. There are multiple methods available for exploring them from high-dimensional data, but almost all of them rely on the assumption that the observations are independent and identically distributed. At the same time, observations connected by a network are becoming increasingly common, and tend to violate these assumptions. Here we develop a Gaussian graphical model for observations connected by a network with potentially different mean vectors, varying smoothly over the network. We propose an efficient estimation algorithm and demonstrate its effectiveness on both simulated and real data, obtaining meaningful and interpretable results on a statistics coauthorship network. We also prove that our method estimates both the inverse covariance matrix and the corresponding graph structure correctly under the assumption of network “cohesion”, which refers to the empirically observed phenomenon of network neighbors sharing similar traits.
Scalable Approximate MCMC Algorithms for the Horseshoe Prior
http://jmlr.org/papers/v21/19-536.html
2020James Johndrow, Paulo Orenstein, Anirban Bhattacharya
The horseshoe prior is frequently employed in Bayesian analysis of high-dimensional models, and has been shown to achieve minimax optimal risk properties when the truth is sparse. While optimization-based algorithms for the extremely popular Lasso and elastic net procedures can scale to dimension in the hundreds of thousands, algorithms for the horseshoe that use Markov chain Monte Carlo (MCMC) for computation are limited to problems an order of magnitude smaller. This is due to high computational cost per step and growth of the variance of time-averaging estimators as a function of dimension. We propose two new MCMC algorithms for computation in these models that have significantly improved performance compared to existing alternatives. One of the algorithms also approximates an expensive matrix product to give orders of magnitude speedup in high-dimensional applications. We prove guarantees for the accuracy of the approximate algorithm, and show that gradually decreasing the approximation error as the chain extends results in an exact algorithm. The scalability of the algorithm is illustrated in simulations with problem size as large as $N=5,000$ observations and $p=50,000$ predictors, and an application to a genome-wide association study with $N=2,267$ and $p=98,385$. The empirical results also show that the new algorithm yields estimates with lower mean squared error, intervals with better coverage, and elucidates features of the posterior that were often missed by previous algorithms in high dimensions, including bimodality of posterior marginals indicating uncertainty about which covariates belong in the model.
(1 + epsilon)-class Classification: an Anomaly Detection Method for Highly Imbalanced or Incomplete Data Sets
http://jmlr.org/papers/v21/19-514.html
2020Maxim Borisyak, Artem Ryzhikov, Andrey Ustyuzhanin, Denis Derkach, Fedor Ratnikov, Olga Mineeva
Anomaly detection is not an easy problem since distribution of anomalous samples is unknown a priori. We explore a novel method that gives a trade-off possibility between one-class and two-class approaches, and leads to a better performance on anomaly detection problems with small or non-representative anomalous samples. The method is evaluated using several data sets and compared to a set of conventional one-class and two-class approaches.
Estimation of a Low-rank Topic-Based Model for Information Cascades
http://jmlr.org/papers/v21/19-496.html
2020Ming Yu, Varun Gupta, Mladen Kolar
We consider the problem of estimating the latent structure of a social network based on the observed information diffusion events, or cascades, where the observations for a given cascade consist of only the timestamps of infection for infected nodes but not the source of the infection. Most of the existing work on this problem has focused on estimating a diffusion matrix without any structural assumptions on it. In this paper, we propose a novel model based on the intuition that an information is more likely to propagate among two nodes if they are interested in similar topics which are also prominent in the information content. In particular, our model endows each node with an influence vector (which measures how authoritative the node is on each topic) and a receptivity vector (which measures how susceptible the node is for each topic). We show how this node-topic structure can be estimated from the observed cascades, and prove the consistency of the estimator. Experiments on synthetic and real data demonstrate the improved performance and better interpretability of our model compared to existing state-of-the-art methods.
Representation Learning for Dynamic Graphs: A Survey
http://jmlr.org/papers/v21/19-447.html
2020Seyed Mehran Kazemi, Rishab Goel, Kshitij Jain, Ivan Kobyzev, Akshay Sethi, Peter Forsyth, Pascal Poupart
Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance. Traditionally, machine learning models for graphs have been mostly designed for static graphs. However, many applications involve evolving graphs. This introduces important challenges for learning and inference since nodes, attributes, and edges change over time. In this survey, we review the recent advances in representation learning for dynamic graphs, including dynamic knowledge graphs. We describe existing models from an encoder-decoder perspective, categorize these encoders and decoders based on the techniques they employ, and analyze the approaches in each category. We also review several prominent applications and widely used datasets and highlight directions for future research.
Union of Low-Rank Tensor Spaces: Clustering and Completion
http://jmlr.org/papers/v21/19-347.html
2020Morteza Ashraphijuo, Xiaodong Wang
We consider the problem of clustering and completing a set of tensors with missing data that are drawn from a union of low-rank tensor spaces. In the clustering problem, given a partially sampled tensor data that is composed of a number of subtensors, each chosen from one of a certain number of unknown tensor spaces, we need to group the subtensors that belong to the same tensor space. We provide a geometrical analysis on the sampling pattern and subsequently derive the sampling rate that guarantees the correct clustering under some assumptions with high probability. Moreover, we investigate the fundamental conditions for finite/unique completability for the union of tensor spaces completion problem. Both deterministic and probabilistic conditions on the sampling pattern to ensure finite/unique completability are obtained. For both the clustering and completion problems, our tensor analysis provides significantly better bound than the bound given by the matrix analysis applied to any unfolding of the tensor data.
On Stationary-Point Hitting Time and Ergodicity of Stochastic Gradient Langevin Dynamics
http://jmlr.org/papers/v21/19-327.html
2020Xi Chen, Simon S. Du, Xin T. Tong
Stochastic gradient Langevin dynamics (SGLD) is a fundamental algorithm in stochastic optimization. Recent work by Zhang et al. (2017) presents an analysis for the hitting time of SGLD for the first and second order stationary points. The proof in Zhang et al. (2017) is a two-stage procedure through bounding the Cheeger's constant, which is rather complicated and leads to loose bounds. In this paper, using intuitions from stochastic differential equations, we provide a direct analysis for the hitting times of SGLD to the first and second order stationary points. Our analysis is straightforward. It only relies on basic linear algebra and probability theory tools. Our direct analysis also leads to tighter bounds comparing to Zhang et al. (2017) and shows the explicit dependence of the hitting time on different factors, including dimensionality, smoothness, noise strength, and step size effects. Under suitable conditions, we show that the hitting time of SGLD to first-order stationary points can be dimension-independent. Moreover, we apply our analysis to study several important online estimation problems in machine learning, including linear regression, matrix factorization, and online PCA.
The weight function in the subtree kernel is decisive
http://jmlr.org/papers/v21/19-290.html
2020Romain Azaïs, Florian Ingels
Tree data are ubiquitous because they model a large variety of situations, e.g., the architecture of plants, the secondary structure of RNA, or the hierarchy of XML files. Nevertheless, the analysis of these non-Euclidean data is difficult per se. In this paper, we focus on the subtree kernel that is a convolution kernel for tree data introduced by Vishwanathan and Smola in the early 2000's. More precisely, we investigate the influence of the weight function from a theoretical perspective and in real data applications. We establish on a 2-classes stochastic model that the performance of the subtree kernel is improved when the weight of leaves vanishes, which motivates the definition of a new weight function, learned from the data and not fixed by the user as usually done. To this end, we define a unified framework for computing the subtree kernel from ordered or unordered trees, that is particularly suitable for tuning parameters. We show through eight real data classification problems the great efficiency of our approach, in particular for small data sets, which also states the high importance of the weight function. Finally, a visualization tool of the significant features is derived.
WONDER: Weighted One-shot Distributed Ridge Regression in High Dimensions
http://jmlr.org/papers/v21/19-277.html
2020Edgar Dobriban, Yue Sheng
In many areas, practitioners need to analyze large data sets that challenge conventional single-machine computing. To scale up data analysis, distributed and parallel computing approaches are increasingly needed. Here we study a fundamental and highly important problem in this area: How to do ridge regression in a distributed computing environment? Ridge regression is an extremely popular method for supervised learning, and has several optimality properties, thus it is important to study. We study one-shot methods that construct weighted combinations of ridge regression estimators computed on each machine. By analyzing the mean squared error in a high-dimensional random-effects model where each predictor has a small effect, we discover several new phenomena. Infinite-worker limit: The distributed estimator works well for very large numbers of machines, a phenomenon we call 'infinite-worker limit'. Optimal weights: The optimal weights for combining local estimators sum to more than unity, due to the downward bias of ridge. Thus, all averaging methods are suboptimal. We also propose a new Weighted ONe-shot DistributEd Ridge regression algorithm (WONDER). We test WONDER in simulation studies and using the Million Song Dataset as an example. There it can save at least 100x in computation time, while nearly preserving test accuracy.
Smoothed Nonparametric Derivative Estimation using Weighted Difference Quotients
http://jmlr.org/papers/v21/19-246.html
2020Yu Liu, Kris De Brabanter
Derivatives play an important role in bandwidth selection methods (e.g., plug-ins), data analysis and bias-corrected confidence intervals. Therefore, obtaining accurate derivative information is crucial. Although many derivative estimation methods exist, the majority require a fixed design assumption. In this paper, we propose an effective and fully data-driven framework to estimate the first and second order derivative in random design. We establish the asymptotic properties of the proposed derivative estimator, and also propose a fast selection method for the tuning parameters. The performance and flexibility of the method is illustrated via an extensive simulation study.
Community-Based Group Graphical Lasso
http://jmlr.org/papers/v21/19-181.html
2020Eugen Pircalabelu, Gerda Claeskens
A new strategy for probabilistic graphical modeling is developed that draws parallels to community detection analysis. The method jointly estimates an undirected graph and homogeneous communities of nodes. The structure of the communities is taken into account when estimating the graph and at the same time, the structure of the graph is accounted for when estimating communities of nodes. The procedure uses a joint group graphical lasso approach with community detection-based grouping, such that some groups of edges co-occur in the estimated graph. The grouping structure is unknown and is estimated based on community detection algorithms. Theoretical derivations regarding graph convergence and sparsistency, as well as accuracy of community recovery are included, while the method's empirical performance is illustrated in an fMRI context, as well as with simulated examples.
Unique Sharp Local Minimum in L1-minimization Complete Dictionary Learning
http://jmlr.org/papers/v21/19-169.html
2020Yu Wang, Siqi Wu, Bin Yu
We study the problem of globally recovering a dictionary from a set of signals via $\ell_1$-minimization. We assume that the signals are generated as i.i.d. random linear combinations of the $K$ atoms from a complete reference dictionary $D^*\in \mathbb R^{K\times K}$, where the linear combination coefficients are from either a Bernoulli type model or exact sparse model. First, we obtain a necessary and sufficient norm condition for the reference dictionary $D^*$ to be a sharp local minimum of the expected $\ell_1$ objective function. Our result substantially extends that of Wu and Yu (2015) and allows the combination coefficient to be non-negative. Secondly, we obtain an explicit bound on the region within which the objective value of the reference dictionary is minimal. Thirdly, we show that the reference dictionary is the unique sharp local minimum, thus establishing the first known global property of $\ell_1$-minimization dictionary learning. Motivated by the theoretical results, we introduce a perturbation based test to determine whether a dictionary is a sharp local minimum of the objective function. In addition, we also propose a new dictionary learning algorithm based on Block Coordinate Descent, called DL-BCD, which is guaranteed to decrease the obective function monotonically. Simulation studies show that DL-BCD has competitive performance in terms of recovery rate compared to other state-of-the-art dictionary learning algorithms when the reference dictionary is generated from random Gaussian matrices.
Generalized Optimal Matching Methods for Causal Inference
http://jmlr.org/papers/v21/19-120.html
2020Nathan Kallus
We develop an encompassing framework for matching, covariate balancing, and doubly-robust methods for causal inference from observational data called generalized optimal matching (GOM). The framework is given by generalizing a new functional-analytical formulation of optimal matching, giving rise to the class of GOM methods, for which we provide a single unified theory to analyze tractability and consistency. Many commonly used existing methods are included in GOM and, using their GOM interpretation, can be extended to optimally and automatically trade off balance for variance and outperform their standard counterparts. As a subclass, GOM gives rise to kernel optimal matching (KOM), which, as supported by new theoretical and empirical results, is notable for combining many of the positive properties of other methods in one. KOM, which is solved as a linearly-constrained convex-quadratic optimization problem, inherits both the interpretability and model-free consistency of matching but can also achieve the $\sqrt{n}$-consistency of well-specified regression and the bias reduction and robustness of doubly robust methods. In settings of limited overlap, KOM enables a very transparent method for interval estimation for partial identification and robust coverage. We demonstrate this in examples with both synthetic and real data.
Multiparameter Persistence Landscapes
http://jmlr.org/papers/v21/19-054.html
2020Oliver Vipond
An important problem in the field of Topological Data Analysis is defining topological summaries which can be combined with traditional data analytic tools. In recent work Bubenik introduced the persistence landscape, a stable representation of persistence diagrams amenable to statistical analysis and machine learning tools. In this paper we generalise the persistence landscape to multiparameter persistence modules providing a stable representation of the rank invariant. We show that multiparameter landscapes are stable with respect to the interleaving distance and persistence weighted Wasserstein distance, and that the collection of multiparameter landscapes faithfully represents the rank invariant. Finally we provide example calculations and statistical tests to demonstrate a range of potential applications and how one can interpret the landscapes associated to a multiparameter module.
Kymatio: Scattering Transforms in Python
http://jmlr.org/papers/v21/19-047.html
2020Mathieu Andreux, Tomás Angles, Georgios Exarchakis, Roberto Leonarduzzi, Gaspar Rochette, Louis Thiry, John Zarka, Stéphane Mallat, Joakim Andén, Eugene Belilovsky, Joan Bruna, Vincent Lostanlen, Muawiz Chaudhary, Matthew J. Hirn, Edouard Oyallon, Sixin Zhang, Carmine Cella, Michael Eickenberg
The wavelet scattering transform is an invariant and stable signal representation suitable for many signal processing and machine learning applications. We present the Kymatio software package, an easy-to-use, high-performance Python implementation of the scattering transform in 1D, 2D, and 3D that is compatible with modern deep learning frameworks, including PyTorch and TensorFlow/Keras. The transforms are implemented on both CPUs and GPUs, the latter offering a significant speedup over the former. The package also has a small memory footprint. Source code, documentation, and examples are available under a BSD license at <a href='https://www.kymat.io'>https://www.kymat.io</a>.
Exact Guarantees on the Absence of Spurious Local Minima for Non-negative Rank-1 Robust Principal Component Analysis
http://jmlr.org/papers/v21/18-884.html
2020Salar Fattahi, Somayeh Sojoudi
This work is concerned with the non-negative rank-1 robust principal component analysis (RPCA), where the goal is to recover the dominant non-negative principal components of a data matrix precisely, where a number of measurements could be grossly corrupted with sparse and arbitrary large noise. Most of the known techniques for solving the RPCA rely on convex relaxation methods by lifting the problem to a higher dimension, which significantly increase the number of variables. As an alternative, the well-known Burer-Monteiro approach can be used to cast the RPCA as a non-convex and non-smooth $\ell_1$ optimization problem with a significantly smaller number of variables. In this work, we show that the low-dimensional formulation of the symmetric and asymmetric positive rank-1 RPCA based on the Burer-Monteiro approach has benign landscape, i.e., 1) it does not have any spurious local solution, 2) has a unique global solution, and 3) its unique global solution coincides with the true components. An implication of this result is that simple local search algorithms are guaranteed to achieve a zero global optimality gap when directly applied to the low-dimensional formulation. Furthermore, we provide strong deterministic and probabilistic guarantees for the exact recovery of the true principal components. In particular, it is shown that a constant fraction of the measurements could be grossly corrupted and yet they would not create any spurious local solution.
Robust Asynchronous Stochastic Gradient-Push: Asymptotically Optimal and Network-Independent Performance for Strongly Convex Functions
http://jmlr.org/papers/v21/18-813.html
2020Artin Spiridonoff, Alex Olshevsky, Ioannis Ch. Paschalidis
We consider the standard model of distributed optimization of a sum of functions $F(\mathbf z) = \sum_{i=1}^n f_i(\mathbf z)$, where node $i$ in a network holds the function $f_i(\mathbf z)$. We allow for a harsh network model characterized by asynchronous updates, message delays, unpredictable message losses, and directed communication among nodes. In this setting, we analyze a modification of the Gradient-Push method for distributed optimization, assuming that (i) node $i$ is capable of generating gradients of its function $f_i(\mathbf z)$ corrupted by zero-mean bounded-support additive noise at each step, (ii) $F(\mathbf z)$ is strongly convex, and (iii) each $f_i(\mathbf z)$ has Lipschitz gradients. We show that our proposed method asymptotically performs as well as the best bounds on centralized gradient descent that takes steps in the direction of the sum of the noisy gradients of all the functions $f_1(\mathbf z), \ldots, f_n(\mathbf z)$ at each step.
Self-paced Multi-view Co-training
http://jmlr.org/papers/v21/18-794.html
2020Fan Ma, Deyu Meng, Xuanyi Dong, Yi Yang
Co-training is a well-known semi-supervised learning approach which trains classifiers on two or more different views and exchanges pseudo labels of unlabeled instances in an iterative way. During the co-training process, pseudo labels of unlabeled instances are very likely to be false especially in the initial training, while the standard co-training algorithm adopts a 'draw without replacement' strategy and does not remove these wrongly labeled instances from training stages. Besides, most of the traditional co-training approaches are implemented for two-view cases, and their extensions in multi-view scenarios are not intuitive. These issues not only degenerate their performance as well as available application range but also hamper their fundamental theory. Moreover, there is no optimization model to explain the objective a co-training process manages to optimize. To address these issues, in this study we design a unified self-paced multi-view co-training (SPamCo) framework which draws unlabeled instances with replacement. Two specified co-regularization terms are formulated to develop different strategies for selecting pseudo-labeled instances during training. Both forms share the same optimization strategy which is consistent with the iteration process in co-training and can be naturally extended to multi-view scenarios. A distributed optimization strategy is also introduced to train the classifier of each view in parallel to further improve the efficiency of the algorithm. Furthermore, the SPamCo algorithm is proved to be PAC learnable, supporting its theoretical soundness. Experiments conducted on synthetic, text categorization, person re-identification, image recognition and object detection data sets substantiate the superiority of the proposed method.
Fast Rates for General Unbounded Loss Functions: From ERM to Generalized Bayes
http://jmlr.org/papers/v21/18-488.html
2020Peter D. Grünwald, Nishant A. Mehta
We present new excess risk bounds for general unbounded loss functions including log loss and squared loss, where the distribution of the losses may be heavy-tailed. The bounds hold for general estimators, but they are optimized when applied to $\eta$-generalized Bayesian, MDL, and empirical risk minimization estimators. In the case of log loss, the bounds imply convergence rates for generalized Bayesian inference under misspecification in terms of a generalization of the Hellinger metric as long as the learning rate $\eta$ is set correctly. For general loss functions, our bounds rely on two separate conditions: the $v$-GRIP (generalized reversed information projection) conditions, which control the lower tail of the excess loss; and the newly introduced witness condition, which controls the upper tail. The parameter $v$ in the $v$-GRIP conditions determines the achievable rate and is akin to the exponent in the Tsybakov margin condition and the Bernstein condition for bounded losses, which the $v$-GRIP conditions generalize; favorable $v$ in combination with small model complexity leads to $\tilde{O}(1/n)$ rates. The witness condition allows us to connect the excess risk to an 'annealed' version thereof, by which we generalize several previous results connecting Hellinger and Rényi divergence to KL divergence.
Conjugate Gradients for Kernel Machines
http://jmlr.org/papers/v21/18-473.html
2020Simon Bartels, Philipp Hennig
Regularized least-squares (kernel-ridge / Gaussian process) regression is a fundamental algorithm of statistics and machine learning. Because generic algorithms for the exact solution have cubic complexity in the number of datapoints, large datasets require to resort to approximations. In this work, the computation of the least-squares prediction is itself treated as a probabilistic inference problem. We propose a structured Gaussian regression model on the kernel function that uses projections of the kernel matrix to obtain a low-rank approximation of the kernel and the matrix. A central result is an enhanced way to use the method of conjugate gradients for the specific setting of least-squares regression as encountered in machine learning.
GraKeL: A Graph Kernel Library in Python
http://jmlr.org/papers/v21/18-370.html
2020Giannis Siglidis, Giannis Nikolentzos, Stratis Limnios, Christos Giatsidis, Konstantinos Skianis, Michalis Vazirgiannis
The problem of accurately measuring the similarity between graphs is at the core of many applications in a variety of disciplines. Graph kernels have recently emerged as a promising approach to this problem. There are now many kernels, each focusing on different structural aspects of graphs. Here, we present GraKeL, a library that unifies several graph kernels into a common framework. The library is written in Python and adheres to the scikit-learn interface. It is simple to use and can be naturally combined with scikit-learn's modules to build a complete machine learning pipeline for tasks such as graph classification and clustering. The code is BSD licensed and is available at: https://github.com/ysig/GraKeL.
High-Dimensional Inference for Cluster-Based Graphical Models
http://jmlr.org/papers/v21/18-357.html
2020Carson Eisenach, Florentina Bunea, Yang Ning, Claudiu Dinicu
Motivated by modern applications in which one constructs graphical models based on a very large number of features, this paper introduces a new class of cluster-based graphical models, in which variable clustering is applied as an initial step for reducing the dimension of the feature space. We employ model assisted clustering, in which the clusters contain features that are similar to the same unobserved latent variable. Two different cluster-based Gaussian graphical models are considered: the latent variable graph, corresponding to the graphical model associated with the unobserved latent variables, and the cluster-average graph, corresponding to the vector of features averaged over clusters. Our study reveals that likelihood based inference for the latent graph, not analyzed previously, is analytically intractable. Our main contribution is the development and analysis of alternative estimation and inference strategies, for the precision matrix of an unobservable latent vector Z. We replace the likelihood of the data by an appropriate class of empirical risk functions, that can be specialized to the latent graphical model and to the simpler, but under-analyzed, cluster-average graphical model. The estimators thus derived can be used for inference on the graph structure, for instance on edge strength or pattern recovery. Inference is based on the asymptotic limits of the entry-wise estimates of the precision matrices associated with the conditional independence graphs under consideration. While taking the uncertainty induced by the clustering step into account, we establish Berry-Esseen central limit theorems for the proposed estimators. It is noteworthy that, although the clusters are estimated adaptively from the data, the central limit theorems regarding the entries of the estimated graphs are proved under the same conditions one would use if the clusters were known in advance. As an illustration of the usage of these newly developed inferential tools, we show that they can be reliably used for recovery of the sparsity pattern of the graphs we study, under FDR control, which is verified via simulation studies and an fMRI data analysis. These experimental results confirm the theoretically established difference between the two graph structures. Furthermore, the data analysis suggests that the latent variable graph, corresponding to the unobserved cluster centers, can help provide more insight into the understanding of the brain connectivity networks relative to the simpler, average-based, graph.
Expected Policy Gradients for Reinforcement Learning
http://jmlr.org/papers/v21/18-012.html
2020Kamil Ciosek, Shimon Whiteson
We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates (or sums) across actions when estimating the gradient, instead of relying only on the action in the sampled trajectory. For continuous action spaces, we first derive a practical result for Gaussian policies and quadratic critics and then extend it to a universal analytical method, covering a broad class of actors and critics, including Gaussian, exponential families, and policies with bounded support. For Gaussian policies, we introduce an exploration method that uses covariance proportional to the matrix exponential of the scaled Hessian of the critic with respect to the actions. For discrete action spaces, we derive a variant of EPG based on softmax policies. We also establish a new general policy gradient theorem, of which the stochastic and deterministic policy gradient theorems are special cases. Furthermore, we prove that EPG reduces the variance of the gradient estimates without requiring deterministic policies and with little computational overhead. Finally, we provide an extensive experimental evaluation of EPG and show that it outperforms existing approaches on multiple challenging control domains.
Learning Causal Networks via Additive Faithfulness
http://jmlr.org/papers/v21/16-252.html
2020Kuang-Yao Lee, Tianqi Liu, Bing Li, Hongyu Zhao
In this paper we introduce a statistical model, called additively faithful directed acyclic graph (AFDAG), for causal learning from observational data. Our approach is based on additive conditional independence (ACI), a recently proposed three-way statistical relation that shares many similarities with conditional independence but without resorting to multi-dimensional kernels. This distinct feature strikes a balance between a parametric model and a fully nonparametric model, which makes the proposed model attractive for handling large networks. We develop an estimator for AFDAG based on a linear operator that characterizes ACI, and establish the consistency and convergence rates of this estimator, as well as the uniform consistency of the estimated DAG. Moreover, we introduce a modified PC-algorithm to implement the estimating procedure efficiently, so that its complexity is determined by the level of sparseness rather than the dimension of the network. Through simulation studies we show that our method outperforms existing methods when commonly assumed conditions such as Gaussian or Gaussian copula distributions do not hold. Finally, the usefulness of AFDAG formulation is demonstrated through an application to a proteomics data set.
Sparse and low-rank multivariate Hawkes processes
http://jmlr.org/papers/v21/15-114.html
2020Emmanuel Bacry, Martin Bompaire, Stéphane Gaïffas, Jean-Francois Muzy
We consider the problem of unveiling the implicit network structure of node interactions (such as user interactions in a social network), based only on high-frequency timestamps. Our inference is based on the minimization of the least-squares loss associated with a multivariate Hawkes model, penalized by $\ell_1$ and trace norm of the interaction tensor. We provide a first theoretical analysis for this problem, that includes sparsity and low-rank inducing penalizations. This result involves a new data-driven concentration inequality for matrix martingales in continuous time with observable variance, which is a result of independent interest and a broad range of possible applications since it extends to matrix martingales former results restricted to the scalar case. A consequence of our analysis is the construction of sharply tuned $\ell_1$ and trace-norm penalizations, that leads to a data-driven scaling of the variability of information available for each users. Numerical experiments illustrate the significant improvements achieved by the use of such data-driven penalizations.
Ensemble Learning for Relational Data
http://jmlr.org/papers/v21/14-368.html
2020Hoda Eldardiry, Jennifer Neville, Ryan A. Rossi
We present a theoretical analysis framework for relational ensemble models. We show that ensembles of collective classifiers can improve predictions for graph data by reducing errors due to variance in both learning and inference. In addition, we propose a relational ensemble framework that combines a relational ensemble learning approach with a relational ensemble inference approach for collective classification. The proposed ensemble techniques are applicable for both single and multiple graph settings. Experiments on both synthetic and real-world data demonstrate the effectiveness of the proposed framework. Finally, our experimental results support the theoretical analysis and confirm that ensemble algorithms that explicitly focus on both learning and inference processes and aim at reducing errors associated with both, are the best performers.
Skill Rating for Multiplayer Games. Introducing Hypernode Graphs and their Spectral Theory
http://jmlr.org/papers/v21/13-561.html
2020Thomas Ricatte, Rémi Gilleron, Marc Tommasi
We consider the skill rating problem for multiplayer games, that is how to infer player skills from game outcomes in multiplayer games. We formulate the problem as a minimization problem $\arg \min_{s} s^T \Delta s$ where $\Delta$ is a positive semidefinite matrix and $s$ a real-valued function, of which some entries are the skill values to be inferred and other entries are constrained by the game outcomes. We leverage graph-based semi-supervised learning (SSL) algorithms for this problem. We apply our algorithms on several data sets of multiplayer games and obtain very promising results compared to Elo Duelling (see Elo, 1978) and TrueSkill (see Herbrich et al., 2006).. As we leverage graph-based SSL algorithms and because games can be seen as relations between sets of players, we then generalize the approach. For this aim, we introduce a new finite model, called hypernode graph, defined to be a set of weighted binary relations between sets of nodes. We define Laplacians of hypernode graphs. Then, we show that the skill rating problem for multiplayer games can be formulated as $\arg \min_{s} s^T \Delta s$ where $\Delta$ is the Laplacian of a hypernode graph constructed from a set of games. From a fundamental perspective, we show that hypernode graph Laplacians are symmetric positive semidefinite matrices with constant functions in their null space. We show that problems on hypernode graphs can not be solved with graph constructions and graph kernels. We relate hypernode graphs to signed graphs showing that positive relations between groups can lead to negative relations between individuals.
Ancestral Gumbel-Top-k Sampling for Sampling Without Replacement
http://jmlr.org/papers/v21/19-985.html
2020Wouter Kool, Herke van Hoof, Max Welling
We develop ancestral Gumbel-Top-$k$ sampling: a generic and efficient method for sampling without replacement from discrete-valued Bayesian networks, which includes multivariate discrete distributions, Markov chains and sequence models. The method uses an extension of the Gumbel-Max trick to sample without replacement by finding the top $k$ of perturbed log-probabilities among all possible configurations of a Bayesian network. Despite the exponentially large domain, the algorithm has a complexity linear in the number of variables and sample size $k$. Our algorithm allows to set the number of parallel processors $m$, to trade off the number of iterations versus the total cost (iterations times $m$) of running the algorithm. For $m = 1$ the algorithm has minimum total cost, whereas for $m = k$ the number of iterations is minimized, and the resulting algorithm is known as Stochastic Beam Search. We provide extensions of the algorithm and discuss a number of related algorithms. We analyze the properties of ancestral Gumbel-Top-$k$ sampling and compare against alternatives on randomly generated Bayesian networks with different levels of connectivity. In the context of (deep) sequence models, we show its use as a method to generate diverse but high-quality translations and statistical estimates of translation quality and entropy.
pyts: A Python Package for Time Series Classification
http://jmlr.org/papers/v21/19-763.html
2020Johann Faouzi, Hicham Janati
pyts is an open-source Python package for time series classification. This versatile toolbox provides implementations of many algorithms published in the literature, preprocessing functionalities, and data set loading utilities. pyts relies on the standard scientific Python packages numpy, scipy, scikit-learn, joblib, and numba, and is distributed under the BSD-3-Clause license. Documentation contains installation instructions, a detailed user guide, a full API description, and concrete self-contained examples.
A Convex Parametrization of a New Class of Universal Kernel Functions
http://jmlr.org/papers/v21/19-594.html
2020Brendon K. Colbert, Matthew M. Peet
The accuracy and complexity of kernel learning algorithms is determined by the set of kernels over which it is able to optimize. An ideal set of kernels should: admit a linear parameterization (tractability); be dense in the set of all kernels (accuracy); and every member should be universal so that the hypothesis space is infinite-dimensional (scalability). Currently, there is no class of kernel that meets all three criteria - e.g. Gaussians are not tractable or accurate; polynomials are not scalable. We propose a new class that meet all three criteria - the Tessellated Kernel (TK) class. Specifically, the TK class: admits a linear parameterization using positive matrices; is dense in all kernels; and every element in the class is universal. This implies that the use of TK kernels for learning the kernel can obviate the need for selecting candidate kernels in algorithms such as SimpleMKL and parameters such as the bandwidth. Numerical testing on soft margin Support Vector Machine (SVM) problems show that algorithms using TK kernels outperform other kernel learning algorithms and neural networks. Furthermore, our results show that when the ratio of the number of training data to features is high, the improvement of TK over MKL increases significantly.
Dynamical Systems as Temporal Feature Spaces
http://jmlr.org/papers/v21/19-589.html
2020Peter Tino
Parametrised state space models in the form of recurrent networks are often used in machine learning to learn from data streams exhibiting temporal dependencies. To break the black box nature of such models it is important to understand the dynamical features of the input-driving time series that are formed in the state space. We propose a framework for rigorous analysis of such state representations in vanishing memory state space models such as echo state networks (ESN). In particular, we consider the state space a temporal feature space and the readout mapping from the state space a kernel machine operating in that feature space. We show that: (1) The usual ESN strategy of randomly generating input-to-state, as well as state coupling leads to shallow memory time series representations, corresponding to cross-correlation operator with fast exponentially decaying coefficients; (2) Imposing symmetry on dynamic coupling yields a constrained dynamic kernel matching the input time series with straightforward exponentially decaying motifs or exponentially decaying motifs of the highest frequency; (3) Simple ring (cycle) high-dimensional reservoir topology specified only through two free parameters can implement deep memory dynamic kernels with a rich variety of matching motifs. We quantify richness of feature representations imposed by dynamic kernels and demonstrate that for dynamic kernel associated with cycle reservoir topology, the kernel richness undergoes a phase transition close to the edge of stability.
Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data
http://jmlr.org/papers/v21/19-569.html
2020Puyudi Yang, Jianbo Chen, Cho-Jui Hsieh, Jane-Ling Wang, Michael I. Jordan
We present a probabilistic framework for studying adversarial attacks on discrete data. Based on this framework, we derive a perturbation-based method, Greedy Attack, and a scalable learning-based method, Gumbel Attack, that illustrate various tradeoffs in the design of attacks. We demonstrate the effectiveness of these methods using both quantitative metrics and human evaluation on various state-of-the-art models for text classification, including a word-based CNN, a character-based CNN and an LSTM. As an example of our results, we show that the accuracy of character-based convolutional networks drops to the level of random selection by modifying only five characters through Greedy Attack.
Branch and Bound for Piecewise Linear Neural Network Verification
http://jmlr.org/papers/v21/19-468.html
2020Rudy Bunel, Jingyue Lu, Ilker Turkaslan, Philip H.S. Torr, Pushmeet Kohli, M. Pawan Kumar
The success of Deep Learning and its potential use in many safety-critical applicationshas motivated research on formal verification of Neural Network (NN) models. In thiscontext, verification involves proving or disproving that an NN model satisfies certaininput-output properties. Despite the reputation of learned NN models as black boxes,and the theoretical hardness of proving useful properties about them, researchers havebeen successful in verifying some classes of models by exploiting their piecewise linearstructure and taking insights from formal methods such as Satisifiability Modulo Theory.However, these methods are still far from scaling to realistic neural networks. To facilitateprogress on this crucial area, we exploit the Mixed Integer Linear Programming (MIP) formulation of verification to propose a family of algorithms based on Branch-and-Bound (BaB). We show that our family contains previous verification methods as special cases.With the help of the BaB framework, we make three key contributions. Firstly, we identifynew methods that combine the strengths of multiple existing approaches, accomplishingsignificant performance improvements over previous state of the art. Secondly, we introducean effective branching strategy on ReLU non-linearities. This branching strategy allows usto efficiently and successfully deal with high input dimensional problems with convolutionalnetwork architecture, on which previous methods fail frequently. Finally, we proposecomprehensive test data sets and benchmarks which includes a collection of previouslyreleased testcases. We use the data sets to conduct a thorough experimental comparison ofexisting and new algorithms and to provide an inclusive analysis of the factors impactingthe hardness of verification problems.
Switching Regression Models and Causal Inference in the Presence of Discrete Latent Variables
http://jmlr.org/papers/v21/19-407.html
2020Rune Christiansen, Jonas Peters
Given a response $Y$ and a vector $X = (X^1, \dots, X^d)$ of $d$ predictors, we investigate the problem of inferring direct causes of $Y$ among the vector $X$. Models for $Y$ that use all of its causal covariates as predictors enjoy the property of being invariant across different environments or interventional settings. Given data from such environments, this property has been exploited for causal discovery. Here, we extend this inference principle to situations in which some (discrete-valued) direct causes of $ Y $ are unobserved. Such cases naturally give rise to switching regression models. We provide sufficient conditions for the existence, consistency and asymptotic normality of the MLE in linear switching regression models with Gaussian noise, and construct a test for the equality of such models. These results allow us to prove that the proposed causal discovery method obtains asymptotic false discovery control under mild conditions. We provide an algorithm, make available code, and test our method on simulated data. It is robust against model violations and outperforms state-of-the-art approaches. We further apply our method to a real data set, where we show that it does not only output causal predictors, but also a process-based clustering of data points, which could be of additional interest to practitioners.
Optimal Bipartite Network Clustering
http://jmlr.org/papers/v21/19-299.html
2020Zhixin Zhou, Arash A. Amini
We study bipartite community detection in networks, or more generally the network biclustering problem. We present a fast two-stage procedure based on spectral initialization followed by the application of a pseudo-likelihood classifier twice. Under mild regularity conditions, we establish the weak consistency of the procedure (i.e., the convergence of the misclassification rate to zero) under a general bipartite stochastic block model. We show that the procedure is optimal in the sense that it achieves the optimal convergence rate that is achievable by a biclustering oracle, adaptively over the whole class, up to constants. This is further formalized by deriving a minimax lower bound over a class of biclustering problems. The optimal rate we obtain sharpens some of the existing results and generalizes others to a wide regime of average degree growth, from sparse networks with average degrees growing arbitrarily slowly to fairly dense networks with average degrees of order $\sqrt{n}$. As a special case, we recover the known exact recovery threshold in the $\log n$ regime of sparsity. To obtain the consistency result, as part of the provable version of the algorithm, we introduce a sub-block partitioning scheme that is also computationally attractive, allowing for distributed implementation of the algorithm without sacrificing optimality. The provable algorithm is derived from a general class of pseudo-likelihood biclustering algorithms that employ simple EM type updates. We show the effectiveness of this general class by numerical simulations.
Learning Linear Non-Gaussian Causal Models in the Presence of Latent Variables
http://jmlr.org/papers/v21/19-260.html
2020Saber Salehkaleybar, AmirEmad Ghassami, Negar Kiyavash, Kun Zhang
We consider the problem of learning causal models from observational data generated by linear non-Gaussian acyclic causal models with latent variables. Without considering the effect of latent variables, the inferred causal relationships among the observed variables are often wrong. Under faithfulness assumption, we propose a method to check whether there exists a causal path between any two observed variables. From this information, we can obtain the causal order among the observed variables. The next question is whether the causal effects can be uniquely identified as well. We show that causal effects among observed variables cannot be identified uniquely under mere assumptions of faithfulness and non-Gaussianity of exogenous noises. However, we are able to propose an efficient method that identifies the set of all possible causal effects that are compatible with the observational data. We present additional structural conditions on the causal graph under which causal effects among observed variables can be determined uniquely. Furthermore, we provide necessary and sufficient graphical conditions for unique identification of the number of variables in the system. Experiments on synthetic data and real-world data show the effectiveness of our proposed algorithm for learning causal models.
Latent Simplex Position Model: High Dimensional Multi-view Clustering with Uncertainty Quantification
http://jmlr.org/papers/v21/19-239.html
2020Leo L. Duan
High dimensional data often contain multiple facets, and several clustering patterns can co-exist under different variable subspaces, also known as the views. While multi-view clustering algorithms were proposed, the uncertainty quantification remains difficult --- a particular challenge is in the high complexity of estimating the cluster assignment probability under each view, and sharing information among views. In this article, we propose an approximate Bayes approach --- treating the similarity matrices generated over the views as rough first-stage estimates for the co-assignment probabilities; in its Kullback-Leibler neighborhood, we obtain a refined low-rank matrix, formed by the pairwise product of simplex coordinates. Interestingly, each simplex coordinate directly encodes the cluster assignment uncertainty. For multi-view clustering, we let each view draw a parameterization from a few candidates, leading to dimension reduction. With high model flexibility, the estimation can be efficiently carried out as a continuous optimization problem, hence enjoys gradient-based computation. The theory establishes the connection of this model to a random partition distribution under multiple views. Compared to single-view clustering approaches, substantially more interpretable results are obtained when clustering brains from a human traumatic brain injury study, using high-dimensional gene expression data.
Causal Discovery Toolbox: Uncovering causal relationships in Python
http://jmlr.org/papers/v21/19-187.html
2020Diviyan Kalainathan, Olivier Goudet, Ritik Dutta
This paper presents a new open source Python framework for causal discovery from observational data and domain background knowledge, aimed at causal graph and causal mechanism modeling. The cdt package implements an end-to-end approach, recovering the direct dependencies (the skeleton of the causal graph) and the causal relationships between variables. It includes algorithms from the `Bnlearn' and `Pcalg' packages, together with algorithms for pairwise causal discovery such as ANM.
Noise Accumulation in High Dimensional Classification and Total Signal Index
http://jmlr.org/papers/v21/19-117.html
2020Miriam R. Elman, Jessica Minnier, Xiaohui Chang, Dongseok Choi
Great attention has been paid to Big Data in recent years. Such data hold promise for scientific discoveries but also pose challenges to analyses. One potential challenge is noise accumulation. In this paper, we explore noise accumulation in high dimensional two-group classification. First, we revisit a previous assessment of noise accumulation with principal component analyses, which yields a different threshold for discriminative ability than originally identified. Then we extend our scope to its impact on classifiers developed with three common machine learning approaches---random forest, support vector machine, and boosted classification trees. We simulate four scenarios with differing amounts of signal strength to evaluate each method. After determining noise accumulation may affect the performance of these classifiers, we assess factors that impact it. We conduct simulations by varying sample size, signal strength, signal strength proportional to the number predictors, and signal magnitude with random forest classifiers. These simulations suggest that noise accumulation affects the discriminative ability of high-dimensional classifiers developed using common machine learning methods, which can be modified by sample size, signal strength, and signal magnitude. We developed the measure total signal index (TSI) to track the trends of total signal and noise accumulation.
Learning with Fenchel-Young losses
http://jmlr.org/papers/v21/19-021.html
2020Mathieu Blondel, André F.T. Martins, Vlad Niculae
Over the past decades, numerous loss functions have been been proposed for a variety of supervised learning tasks, including regression, classification, ranking, and more generally structured prediction. Understanding the core principles and theoretical properties underpinning these losses is key to choose the right loss for the right problem, as well as to create new losses which combine their strengths. In this paper, we introduce Fenchel-Young losses, a generic way to construct a convex loss function for a regularized prediction function. We provide an in-depth study of their properties in a very broad setting, covering all the aforementioned supervised learning tasks, and revealing new connections between sparsity, generalized entropies, and separation margins. We show that Fenchel-Young losses unify many well-known loss functions and allow to create useful new ones easily. Finally, we derive efficient predictive and training algorithms, making Fenchel-Young losses appealing both in theory and practice.
Graph-Dependent Implicit Regularisation for Distributed Stochastic Subgradient Descent
http://jmlr.org/papers/v21/18-638.html
2020Dominic Richards, Patrick Rebeschini
We propose graph-dependent implicit regularisation strategies for synchronised distributed stochastic subgradient descent (Distributed SGD) for convex problems in multi-agent learning. Under the standard assumptions of convexity, Lipschitz continuity, and smoothness, we establish statistical learning rates that retain, up to logarithmic terms, single-machine serial statistical guarantees through implicit regularisation (step size tuning and early stopping) with appropriate dependence on the graph topology. Our approach avoids the need for explicit regularisation in decentralised learning problems, such as adding constraints to the empirical risk minimisation rule. Particularly for distributed methods, the use of implicit regularisation allows the algorithm to remain simple, without projections or dual methods. To prove our results, we establish graph-independent generalisation bounds for Distributed SGD that match the single-machine serial SGD setting (using algorithmic stability), and we establish graph-dependent optimisation bounds that are of independent interest. We present numerical experiments to show that the qualitative nature of the upper bounds we derive can be representative of real behaviours.
On the Complexity Analysis of the Primal Solutions for the Accelerated Randomized Dual Coordinate Ascent
http://jmlr.org/papers/v21/18-425.html
2020Huan Li, Zhouchen Lin
Dual first-order methods are essential techniques for large-scale constrained convex optimization. However, when recovering the primal solutions, we need $T(\epsilon^{-2})$ iterations to achieve an $\epsilon$-optimal primal solution when we apply an algorithm to the non-strongly convex dual problem with $T(\epsilon^{-1})$ iterations to achieve an $\epsilon$-optimal dual solution, where $T(x)$ can be $x$ or $\sqrt{x}$. In this paper, we prove that the iteration complexity of the primal solutions and dual solutions have the same $O\left(\frac{1}{\sqrt{\epsilon}}\right)$ order of magnitude for the accelerated randomized dual coordinate ascent. When the dual function further satisfies the quadratic functional growth condition, by restarting the algorithm at any period, we establish the linear iteration complexity for both the primal solutions and dual solutions even if the condition number is unknown. When applied to the regularized empirical risk minimization problem, we prove the iteration complexity of $O\left(n\log n+\sqrt{\frac{n}{\epsilon}}\right)$ in both primal space and dual space, where $n$ is the number of samples. Our result takes out the $\left(\log \frac{1}{\epsilon}\right)$ factor compared with the methods based on smoothing/regularization or Catalyst reduction. As far as we know, this is the first time that the optimal $O\left(\sqrt{\frac{n}{\epsilon}}\right)$ iteration complexity in the primal space is established for the dual coordinate ascent based stochastic algorithms. We also establish the accelerated linear complexity for some problems with nonsmooth loss, e.g., the least absolute deviation and SVM.
Provably robust estimation of modulo 1 samples of a smooth function with applications to phase unwrapping
http://jmlr.org/papers/v21/18-143.html
2020Mihai Cucuringu, Hemant Tyagi
Consider an unknown smooth function $f: [0,1]^d \rightarrow \mathbb{R}$, and assume we are given $n$ noisy mod 1 samples of $f$, i.e., $y_i = (f(x_i) + \eta_i) \bmod 1$, for $x_i \in [0,1]^d$, where $\eta_i$ denotes the noise. Given the samples $(x_i,y_i)_{i=1}^{n}$, our goal is to recover smooth, robust estimates of the clean samples $f(x_i) \bmod 1$. We formulate a natural approach for solving this problem, which works with angular embeddings of the noisy mod 1 samples over the unit circle, inspired by the angular synchronization framework. This amounts to solving a smoothness regularized least-squares problem -- a quadratically constrained quadratic program (QCQP) -- where the variables are constrained to lie on the unit circle. Our proposed approach is based on solving its relaxation, which is a trust-region sub-problem and hence solvable efficiently. We provide theoretical guarantees demonstrating its robustness to noise for adversarial, as well as random Gaussian and Bernoulli noise models. To the best of our knowledge, these are the first such theoretical results for this problem. We demonstrate the robustness and efficiency of our proposed approach via extensive numerical simulations on synthetic data, along with a simple least-squares based solution for the unwrapping stage, that recovers the original samples of $f$ (up to a global shift). It is shown to perform well at high levels of noise, when taking as input the denoised modulo $1$ samples. Finally, we also consider two other approaches for denoising the modulo 1 samples that leverage tools from Riemannian optimization on manifolds, including a Burer-Monteiro approach for a semidefinite programming relaxation of our formulation. For the two-dimensional version of the problem, which has applications in synthetic aperture radar interferometry (InSAR), we are able to solve instances of real-world data with a million sample points in under 10 seconds, on a personal laptop.
Generalized Nonbacktracking Bounds on the Influence
http://jmlr.org/papers/v21/18-112.html
2020Emmanuel Abbe, Sanjeev Kulkarni, Eun Jee Lee
This paper develops deterministic upper and lower bounds on the influence measure in a network, more precisely, the expected number of nodes that a seed set can influence in the independent cascade model. In particular, our bounds exploit r-nonbacktracking walks and Fortuin-Kasteleyn-Ginibre (FKG) type inequalities, and are computed by message passing algorithms. Further, we provide parameterized versions of the bounds that control the trade-off between efficiency and accuracy. Finally, the tightness of the bounds is illustrated on various network models.
Tensor Train Decomposition on TensorFlow (T3F)
http://jmlr.org/papers/v21/18-008.html
2020Alexander Novikov, Pavel Izmailov, Valentin Khrulkov, Michael Figurnov, Ivan Oseledets
Tensor Train decomposition is used across many branches of machine learning. We present T3F—a library for Tensor Train decomposition based on TensorFlow. T3F supports GPU execution, batch processing, automatic differentiation, and versatile functionality for the Riemannian optimization framework, which takes into account the underlying manifold structure to construct efficient optimization methods. The library makes it easier to implement machine learning papers that rely on the Tensor Train decomposition. T3F includes documentation, examples and 94% test coverage.
The Maximum Separation Subspace in Sufficient Dimension Reduction with Categorical Response
http://jmlr.org/papers/v21/17-788.html
2020Xin Zhang, Qing Mai, Hui Zou
Sufficient dimension reduction (SDR) is a very useful concept for exploratory analysis and data visualization in regression, especially when the number of covariates is large. Many SDR methods have been proposed for regression with a continuous response, where the central subspace (CS) is the target of estimation. Various conditions, such as the linearity condition and the constant covariance condition, are imposed so that these methods can estimate at least a portion of the CS. In this paper we study SDR for regression and discriminant analysis with categorical response. Motivated by the exploratory analysis and data visualization aspects of SDR, we propose a new geometric framework to reformulate the SDR problem in terms of manifold optimization and introduce a new concept called Maximum Separation Subspace (MASES). The MASES naturally preserves the “sufficiency” in SDR without imposing additional conditions on the predictor distribution, and directly inspires a semi-parametric estimator. Numerical studies show MASES exhibits superior performance as compared with competing SDR methods in specific settings.
On the consistency of graph-based Bayesian semi-supervised learning and the scalability of sampling algorithms
http://jmlr.org/papers/v21/17-698.html
2020Nicolas Garcia Trillos, Zachary Kaplan, Thabo Samakhoana, Daniel Sanz-Alonso
This paper considers a Bayesian approach to graph-based semi-supervised learning. We show that if the graph parameters are suitably scaled, the graph-posteriors converge to a continuum limit as the size of the unlabeled data set grows. This consistency result has profound algorithmic implications: we prove that when consistency holds, carefully designed Markov chain Monte Carlo algorithms have a uniform spectral gap, independent of the number of unlabeled inputs. Numerical experiments illustrate and complement the theory.
A New Class of Time Dependent Latent Factor Models with Applications
http://jmlr.org/papers/v21/16-639.html
2020Sinead A. Williamson, Michael Minyi Zhang, Paul Damien
In many applications, observed data are influenced by some combination of latent causes. For example, suppose sensors are placed inside a building to record responses such as temperature, humidity, power consumption and noise levels. These random, observed responses are typically affected by many unobserved, latent factors (or features) within the building such as the number of individuals, the turning on and off of electrical devices, power surges, etc. These latent factors are usually present for a contiguous period of time before disappearing; further, multiple factors could be present at a time.
This paper develops new probabilistic methodology and inference methods for random object generation influenced by latent features exhibiting temporal persistence. Every datum is associated with subsets of a potentially infinite number of hidden, persistent features that account for temporal dynamics in an observation. The ensuing class of dynamic models constructed by adapting the Indian Buffet Process — a probability measure on the space of random, unbounded binary matrices — finds use in a variety of applications arising in operations, signal processing, biomedicine, marketing, image analysis, etc. Illustrations using synthetic and real data are provided.
Targeted Fused Ridge Estimation of Inverse Covariance Matrices from Multiple High-Dimensional Data Classes
http://jmlr.org/papers/v21/15-509.html
2020Anders Ellern Bilgrau, Carel F.W. Peeters, Poul Svante Eriksen, Martin Boegsted, Wessel N. van Wieringen
We consider the problem of jointly estimating multiple inverse covariance matrices from high-dimensional data consisting of distinct classes. An $\ell_2$-penalized maximum likelihood approach is employed. The suggested approach is flexible and generic, incorporating several other $\ell_2$-penalized estimators as special cases. In addition, the approach allows specification of target matrices through which prior knowledge may be incorporated and which can stabilize the estimation procedure in high-dimensional settings. The result is a targeted fused ridge estimator that is of use when the precision matrices of the constituent classes are believed to chiefly share the same structure while potentially differing in a number of locations of interest. It has many applications in (multi)factorial study designs. We focus on the graphical interpretation of precision matrices with the proposed estimator then serving as a basis for integrative or meta-analytic Gaussian graphical modeling. Situations are considered in which the classes are defined by data sets and subtypes of diseases. The performance of the proposed estimator in the graphical modeling setting is assessed through extensive simulation experiments. Its practical usability is illustrated by the differential network modeling of 12 large-scale gene expression data sets of diffuse large B-cell lymphoma subtypes. The estimator and its related procedures are incorporated into the R-package rags2ridges.
Lower Bounds for Testing Graphical Models: Colorings and Antiferromagnetic Ising Models
http://jmlr.org/papers/v21/19-580.html
2020Ivona Bezáková, Antonio Blanca, Zongchen Chen, Daniel Štefankovič, Eric Vigoda
We study the identity testing problem in the context of spin systems or undirected graphical models, where it takes the following form: given the parameter specification of the model $M$ and a sampling oracle for the distribution $\mu_{M^*}$ of an unknown model $M^*$, can we efficiently determine if the two models $M$ and $M^*$ are the same? We consider identity testing for both soft-constraint and hard-constraint systems. In particular, we prove hardness results in two prototypical cases, the Ising model and proper colorings, and explore whether identity testing is any easier than structure learning. For the ferromagnetic (attractive) Ising model, Daskalakis et al. (2018) presented a polynomial-time algorithm for identity testing. We prove hardness results in the antiferromagnetic (repulsive) setting in the same regime of parameters where structure learning is known to require a super-polynomial number of samples. Specifically, for $n$-vertex graphs of maximum degree $d$, we prove that if $|\beta| d = \omega(\log{n})$ (where $\beta$ is the inverse temperature parameter), then there is no polynomial running time identity testing algorithm unless $RP=NP$. In the hard-constraint setting, we present hardness results for identity testing for proper colorings. Our results are based on the presumed hardness of #BIS, the problem of (approximately) counting independent sets in bipartite graphs.
Distributed Feature Screening via Componentwise Debiasing
http://jmlr.org/papers/v21/19-537.html
2020Xingxiang Li, Runze Li, Zhiming Xia, Chen Xu
Feature screening is a powerful tool in processing high-dimensional data. When the sample size N and the number of features p are both large, the implementation of classic screening methods can be numerically challenging. In this paper, we propose a distributed screening framework for big data setup. In the spirit of 'divide-and-conquer', the proposed framework expresses a correlation measure as a function of several component parameters, each of which can be distributively estimated using a natural U-statistic from data segments. With the component estimates aggregated, we obtain a final correlation estimate that can be readily used for screening features. This framework enables distributed storage and parallel computing and thus is computationally attractive. Due to the unbiased distributive estimation of the component parameters, the final aggregated estimate achieves a high accuracy that is insensitive to the number of data segments m. Under mild conditions, we show that the aggregated correlation estimator is as efficient as the centralized estimator in terms of the probability convergence bound and the mean squared error rate; the corresponding screening procedure enjoys sure screening property for a wide range of correlation measures. The promising performances of the new method are supported by extensive numerical examples.
GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
http://jmlr.org/papers/v21/19-429.html
2020Jian Guo, He He, Tong He, Leonard Lausen, Mu Li, Haibin Lin, Xingjian Shi, Chenguang Wang, Junyuan Xie, Sheng Zha, Aston Zhang, Hang Zhang, Zhi Zhang, Zhongyue Zhang, Shuai Zheng, Yi Zhu
We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-the-art pre-trained models, training scripts, and training logs, to facilitate rapid prototyping and promote reproducible research. We also provide modular APIs with flexible building blocks to enable efficient customization. Leveraging the MXNet ecosystem, the deep learning models in GluonCV and GluonNLP can be deployed onto a variety of platforms with different programming languages. The Apache 2.0 license has been adopted by GluonCV and GluonNLP to allow for software distribution, modification, and usage.
A Unified Framework for Structured Graph Learning via Spectral Constraints
http://jmlr.org/papers/v21/19-276.html
2020Sandeep Kumar, Jiaxi Ying, José Vinícius de M. Cardoso, Daniel P. Palomar
Graph learning from data is a canonical problem that has received substantial attention in the literature. Learning a structured graph is essential for interpretability and identification of the relationships among data. In general, learning a graph with a specific structure is an NP-hard combinatorial problem and thus designing a general tractable algorithm is challenging. Some useful structured graphs include connected, sparse, multi-component, bipartite, and regular graphs. In this paper, we introduce a unified framework for structured graph learning that combines Gaussian graphical model and spectral graph theory. We propose to convert combinatorial structural constraints into spectral constraints on graph matrices and develop an optimization framework based on block majorization-minimization to solve structured graph learning problem. The proposed algorithms are provably convergent and practically amenable for a number of graph based applications such as data clustering. Extensive numerical experiments with both synthetic and real data sets illustrate the effectiveness of the proposed algorithms. An open source R package containing the code for all the experiments is available at https://CRAN.R-project.org/package=spectralGraphTopology.
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
http://jmlr.org/papers/v21/19-198.html
2020Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright
We study derivative-free methods for policy optimization over the class of linear policies. We focus on characterizing the convergence rate of these methods when applied to linear-quadratic systems, and study various settings of driving noise and reward feedback. Our main theoretical result provides an explicit bound on the sample or evaluation complexity: we show that these methods are guaranteed to converge to within any pre-specified tolerance of the optimal policy with a number of zero-order evaluations that is an explicit polynomial of the error tolerance, dimension, and curvature properties of the problem. Our analysis reveals some interesting differences between the settings of additive driving noise and random initialization, as well as the settings of one-point and two-point reward feedback. Our theory is corroborated by simulations of derivative-free methods in application to these systems. Along the way, we derive convergence rates for stochastic zero-order optimization algorithms when applied to a certain class of non-convex problems.
Convergences of Regularized Algorithms and Stochastic Gradient Methods with Random Projections
http://jmlr.org/papers/v21/19-083.html
2020Junhong Lin, Volkan Cevher
We study the least-squares regression problem over a Hilbert space, covering nonparametric regression over a reproducing kernel Hilbert space as a special case. We first investigate regularized algorithms adapted to a projection operator on a closed subspace of the Hilbert space. We prove convergence results with respect to variants of norms, under a capacity assumption on the hypothesis space and a regularity condition on the target function. As a result, we obtain optimal rates for regularized algorithms with randomized sketches, provided that the sketch dimension is proportional to the effective dimension up to a logarithmic factor. As a byproduct, we obtain similar results for Nystr\"{o}m regularized algorithms. Our results provide optimal, distribution-dependent rates that do not have any saturation effect for sketched/Nystr\"{o}m regularized algorithms, considering both the attainable and non-attainable cases, in the well-conditioned regimes. We then study stochastic gradient methods with projection over the subspace, allowing multi-pass over the data and minibatches, and we derive similar optimal statistical convergence results.
High-Dimensional Interactions Detection with Sparse Principal Hessian Matrix
http://jmlr.org/papers/v21/19-071.html
2020Cheng Yong Tang, Ethan X. Fang, Yuexiao Dong
In statistical learning framework with regressions, interactions are the contributions to the response variable from the products of the explanatory variables. In high-dimensional problems, detecting interactions is challenging due to combinatorial complexity and limited data information. We consider detecting interactions by exploring their connections with the principal Hessian matrix. Specifically, we propose a one-step synthetic approach for estimating the principal Hessian matrix by a penalized M-estimator. An alternating direction method of multipliers (ADMM) is proposed to efficiently solve the encountered regularized optimization problem. Based on the sparse estimator, we detect the interactions by identifying its nonzero components. Our method directly targets at the interactions, and it requires no structural assumption on the hierarchy of the interactions effects. We show that our estimator is theoretically valid, computationally efficient, and practically useful for detecting the interactions in a broad spectrum of scenarios.
Connecting Spectral Clustering to Maximum Margins and Level Sets
http://jmlr.org/papers/v21/18-850.html
2020David P. Hofmeyr
We study the connections between spectral clustering and the problems of maximum margin clustering, and estimation of the components of level sets of a density function. Specifically, we obtain bounds on the eigenvectors of graph Laplacian matrices in terms of the between cluster separation, and within cluster connectivity. These bounds ensure that the spectral clustering solution converges to the maximum margin clustering solution as the scaling parameter is reduced towards zero. The sensitivity of maximum margin clustering solutions to outlying points is well known, but can be mitigated by first removing such outliers, and applying maximum margin clustering to the remaining points. If outliers are identified using an estimate of the underlying probability density, then the remaining points may be seen as an estimate of a level set of this density function. We show that such an approach can be used to consistently estimate the components of the level sets of a density function under very mild assumptions.
Expectation Propagation as a Way of Life: A Framework for Bayesian Inference on Partitioned Data
http://jmlr.org/papers/v21/18-817.html
2020Aki Vehtari, Andrew Gelman, Tuomas Sivula, Pasi Jylänki, Dustin Tran, Swupnil Sahai, Paul Blomstedt, John P. Cunningham, David Schiminovich, Christian P. Robert
A common divide-and-conquer approach for Bayesian computation with big data is to partition the data, perform local inference for each piece separately, and combine the results to obtain a global posterior approximation. While being conceptually and computationally appealing, this method involves the problematic need to also split the prior for the local inferences; these weakened priors may not provide enough regularization for each separate computation, thus eliminating one of the key advantages of Bayesian methods. To resolve this dilemma while still retaining the generalizability of the underlying local inference method, we apply the idea of expectation propagation (EP) as a framework for distributed Bayesian inference. The central idea is to iteratively update approximations to the local likelihoods given the state of the other approximations and the prior. The present paper has two roles: we review the steps that are needed to keep EP algorithms numerically stable, and we suggest a general approach, inspired by EP, for approaching data partitioning problems in a way that achieves the computational benefits of parallelism while allowing each local update to make use of relevant information from the other sites. In addition, we demonstrate how the method can be applied in a hierarchical context to make use of partitioning of both data and parameters. The paper describes a general algorithmic framework, rather than a specific algorithm, and presents an example implementation for it.
Practical Locally Private Heavy Hitters
http://jmlr.org/papers/v21/18-786.html
2020Raef Bassily, Kobbi Nissim, Uri Stemmer, Abhradeep Thakurta
We present new practical local differentially private heavy hitters algorithms achieving optimal or near-optimal worst-case error and running time -- TreeHist and Bitstogram. In both algorithms, server running time is $\tilde O(n)$ and user running time is $\tilde O(1)$, hence improving on the prior state-of-the-art result of Bassily and Smith [STOC 2015] requiring $O(n^{5/2})$ server time and $O(n^{3/2})$ user time. With a typically large number of participants in local algorithms (in the millions), this reduction in time complexity, in particular at the user side, is crucial for making locally private heavy hitters algorithms usable in practice. We implemented Algorithm TreeHist to verify our theoretical analysis and compared its performance with the performance of Google's RAPPOR code.
Perturbation Bounds for Procrustes, Classical Scaling, and Trilateration, with Applications to Manifold Learning
http://jmlr.org/papers/v21/18-720.html
2020Ery Arias-Castro, Adel Javanmard, Bruno Pelletier
One of the common tasks in unsupervised learning is dimensionality reduction, where the goal is to find meaningful low-dimensional structures hidden in high-dimensional data. Sometimes referred to as manifold learning, this problem is closely related to the problem of localization, which aims at embedding a weighted graph into a low-dimensional Euclidean space. Several methods have been proposed for localization, and also manifold learning. Nonetheless, the robustness property of most of them is little understood. In this paper, we obtain perturbation bounds for classical scaling and trilateration, which are then applied to derive performance bounds for Isomap, Landmark Isomap, and Maximum Variance Unfolding. A new perturbation bound for procrustes analysis plays a key role.
On lp-Support Vector Machines and Multidimensional Kernels
http://jmlr.org/papers/v21/18-601.html
2020Victor Blanco, Justo Puerto, Antonio M. Rodriguez-Chia
In this paper, we extend the methodology developed for Support Vector Machines (SVM) using the $\ell_2$-norm ($\ell_2$-SVM) to the more general case of $\ell_p$-norms with $p>1$ ($\ell_p$-SVM). We derive second order cone formulations for the resulting dual and primal problems. The concept of kernel function, widely applied in $\ell_2$-SVM, is extended to the more general case of $\ell_p$-norms with $p>1$ by defining a new operator called multidimensional kernel. This object gives rise to reformulations of dual problems, in a transformed space of the original data, where the dependence on the original data always appear as homogeneous polynomials. We adapt known solution algorithms to efficiently solve the primal and dual resulting problems and some computational experiments on real-world datasets are presented showing rather good behavior in terms of the accuracy of $\ell_p$-SVM with $p>1$.
Generalized probabilistic principal component analysis of correlated data
http://jmlr.org/papers/v21/18-595.html
2020Mengyang Gu, Weining Shen
Principal component analysis (PCA) is a well-established tool in machine learning and data processing. The principal axes in PCA were shown to be equivalent to the maximum marginal likelihood estimator of the factor loading matrix in a latent factor model for the observed data, assuming that the latent factors are independently distributed as standard normal distributions. However, the independence assumption may be unrealistic for many scenarios such as modeling multiple time series, spatial processes, and functional data, where the outcomes are correlated. In this paper, we introduce the generalized probabilistic principal component analysis (GPPCA) to study the latent factor model for multiple correlated outcomes, where each factor is modeled by a Gaussian process. Our method generalizes the previous probabilistic formulation of PCA (PPCA) by providing the closed-form maximum marginal likelihood estimator of the factor loadings and other parameters. Based on the explicit expression of the precision matrix in the marginal likelihood that we derived, the number of the computational operations is linear to the number of output variables. Furthermore, we also provide the closed-form expression of the marginal likelihood when other covariates are included in the mean structure. We highlight the advantage of GPPCA in terms of the practical relevance, estimation accuracy and computational convenience. Numerical studies of simulated and real data confirm the excellent finite-sample performance of the proposed approach.
Neyman-Pearson classification: parametrics and sample size requirement
http://jmlr.org/papers/v21/18-577.html
2020Xin Tong, Lucy Xia, Jiacheng Wang, Yang Feng
The Neyman-Pearson (NP) paradigm in binary classification seeks classifiers that achieve a minimal type II error while enforcing the prioritized type I error controlled under some user-specified level $\alpha$. This paradigm serves naturally in applications such as severe disease diagnosis and spam detection, where people have clear priorities among the two error types. Recently, Tong, Feng, and Li (2018) proposed a nonparametric umbrella algorithm that adapts all scoring-type classification methods (e.g., logistic regression, support vector machines, random forest) to respect the given type I error (i.e., conditional probability of classifying a class $0$ observation as class $1$ under the 0-1 coding) upper bound $\alpha$ with high probability, without specific distributional assumptions on the features and the responses. Universal the umbrella algorithm is, it demands an explicit minimum sample size requirement on class $0$, which is often the more scarce class, such as in rare disease diagnosis applications. In this work, we employ the parametric linear discriminant analysis (LDA) model and propose a new parametric thresholding algorithm, which does not need the minimum sample size requirements on class $0$ observations and thus is suitable for small sample applications such as rare disease diagnosis. Leveraging both the existing nonparametric and the newly proposed parametric thresholding rules, we propose four LDA-based NP classifiers, for both low- and high-dimensional settings. On the theoretical front, we prove NP oracle inequalities for one proposed classifier, where the rate for excess type II error benefits from the explicit parametric model assumption. Furthermore, as NP classifiers involve a sample splitting step of class $0$ observations, we construct a new adaptive sample splitting scheme that can be applied universally to NP classifiers, and this adaptive strategy reduces the type II error of these classifiers. The proposed NP classifiers are implemented in the R package nproc.
Weighted Message Passing and Minimum Energy Flow for Heterogeneous Stochastic Block Models with Side Information
http://jmlr.org/papers/v21/18-573.html
2020T. Tony Cai, Tengyuan Liang, Alexander Rakhlin
We study the misclassification error for community detection in general heterogeneous stochastic block models (SBM) with noisy or partial label information. We establish a connection between the misclassification rate and the notion of minimum energy on the local neighborhood of the SBM. We develop an optimally weighted message passing algorithm to reconstruct labels for SBM based on the minimum energy flow and the eigenvectors of a certain Markov transition matrix. The general SBM considered in this paper allows for unequal-size communities, degree heterogeneity, and different connection probabilities among blocks. We focus on how to optimally weigh the message passing to improve misclassification.
Online Sufficient Dimension Reduction Through Sliced Inverse Regression
http://jmlr.org/papers/v21/18-567.html
2020Zhanrui Cai, Runze Li, Liping Zhu
Sliced inverse regression is an effective paradigm that achieves the goal of dimension reduction through replacing high dimensional covariates with a small number of linear combinations. It does not impose parametric assumptions on the dependence structure. More importantly, such a reduction of dimension is sufficient in that it does not cause loss of information. In this paper, we adapt the stationary sliced inverse regression to cope with the rapidly changing environments. We propose to implement sliced inverse regression in an online fashion. This online learner consists of two steps. In the first step we construct an online estimate for the kernel matrix; in the second step we propose two online algorithms, one is motivated by the perturbation method and the other is originated from the gradient descent optimization, to perform online singular value decomposition. The theoretical properties of this online learner are established. We demonstrate the numerical performance of this online learner through simulations and real world applications. All numerical studies confirm that this online learner performs as well as the batch learner.
On Mahalanobis Distance in Functional Settings
http://jmlr.org/papers/v21/18-156.html
2020José R. Berrendero, Beatriz Bueno-Larraz, Antonio Cuevas
Mahalanobis distance is a classical tool in multivariate analysis. We suggest here an extension of this concept to the case of functional data. More precisely, the proposed definition concerns those statistical problems where the sample data are real functions defined on a compact interval of the real line. The obvious difficulty for such a functional extension is the non-invertibility of the covariance operator in infinite-dimensional cases. Unlike other recent proposals, our definition is suggested and motivated in terms of the Reproducing Kernel Hilbert Space (RKHS) associated with the stochastic process that generates the data. The proposed distance is a true metric; it depends on a unique real smoothing parameter which is fully motivated in RKHS terms. Moreover, it shares some properties of its finite dimensional counterpart: it is invariant under isometries, it can be consistently estimated from the data and its sampling distribution is known under Gaussian models. An empirical study for two statistical applications, outliers detection and binary classification, is included. The results are quite competitive when compared to other recent proposals in the literature.
DESlib: A Dynamic ensemble selection library in Python
http://jmlr.org/papers/v21/18-144.html
2020Rafael M. O. Cruz, Luiz G. Hafemann, Robert Sabourin, George D. C. Cavalcanti
DESlib is an open-source python library providing the implementation of several dynamic selection techniques. The library is divided into three modules: (i) dcs, containing the implementation of dynamic classifier selection methods (DCS); (ii) des, containing the implementation of dynamic ensemble selection methods (DES); (iii) static, with the implementation of static ensemble techniques. The library is fully documented (documentation available online on Read the Docs), has a high test coverage (codecov.io) and is part of the scikit-learn-contrib supported projects. Documentation, code and examples can be found on its GitHub page: https://github.com/scikit-learn-contrib/DESlib.
Target Propagation in Recurrent Neural Networks
http://jmlr.org/papers/v21/18-141.html
2020Nikolay Manchev, Michael Spratling
Recurrent Neural Networks have been widely used to process sequence data, but have long been criticized for their biological implausibility and training difficulties related to vanishing and exploding gradients. This paper presents a novel algorithm for training recurrent networks, target propagation through time (TPTT), that outperforms standard backpropagation through time (BPTT) on four out of the five problems used for testing. The proposed algorithm is initially tested and compared to BPTT on four synthetic time lag tasks, and its performance is also measured using the sequential MNIST data set. In addition, as TPTT uses target propagation, it allows for discrete nonlinearities and could potentially mitigate the credit assignment problem in more complex recurrent architectures.
Path-Based Spectral Clustering: Guarantees, Robustness to Outliers, and Fast Algorithms
http://jmlr.org/papers/v21/18-085.html
2020Anna Little, Mauro Maggioni, James M. Murphy
We consider the problem of clustering with the longest-leg path distance (LLPD) metric, which is informative for elongated and irregularly shaped clusters. We prove finite-sample guarantees on the performance of clustering with respect to this metric when random samples are drawn from multiple intrinsically low-dimensional clusters in high-dimensional space, in the presence of a large number of high-dimensional outliers. By combining these results with spectral clustering with respect to LLPD, we provide conditions under which the Laplacian eigengap statistic correctly determines the number of clusters for a large class of data sets, and prove guarantees on the labeling accuracy of the proposed algorithm. Our methods are quite general and provide performance guarantees for spectral clustering with any ultrametric. We also introduce an efficient, easy to implement approximation algorithm for the LLPD based on a multiscale analysis of adjacency graphs, which allows for the runtime of LLPD spectral clustering to be quasilinear in the number of data points.
Lower Bounds for Parallel and Randomized Convex Optimization
http://jmlr.org/papers/v21/19-771.html
2020Jelena Diakonikolas, Cristóbal Guzmán
We study the question of whether parallelization in the exploration of the feasible set can be used to speed up convex optimization, in the local oracle model of computation and in the high-dimensional regime. We show that the answer is negative for both deterministic and randomized algorithms applied to essentially any of the interesting geometries and nonsmooth, weakly-smooth, or smooth objective functions. In particular, we show that it is not possible to obtain a polylogarithmic (in the sequential complexity of the problem) number of parallel rounds with a polynomial (in the dimension) number of queries per round. In the majority of these settings and when the dimension of the space is polynomial in the inverse target accuracy, our lower bounds match the oracle complexity of sequential convex optimization, up to at most a logarithmic factor in the dimension, which makes them (nearly) tight. Another conceptual contribution of our work is in providing a general and streamlined framework for proving lower bounds in the setting of parallel convex optimization. Prior to our work, lower bounds for parallel convex optimization algorithms were only known in a small fraction of the settings considered in this paper, mainly applying to Euclidean ($\ell_2$) and $\ell_\infty$ spaces.
Universal Latent Space Model Fitting for Large Networks with Edge Covariates
http://jmlr.org/papers/v21/17-470.html
2020Zhuang Ma, Zongming Ma, Hongsong Yuan
Latent space models are effective tools for statistical modeling and visualization of network data. Due to their close connection to generalized linear models, it is also natural to incorporate covariate information in them. The current paper presents two universal fitting algorithms for networks with edge covariates: one based on nuclear norm penalization and the other based on projected gradient descent. Both algorithms are motivated by maximizing the likelihood function for an existing class of inner-product models, and we establish their statistical rates of convergence for these models. In addition, the theory informs us that both methods work simultaneously for a wide range of different latent space models that allow latent positions to affect edge formation in flexible ways, such as distance models. Furthermore, the effectiveness of the methods is demonstrated on a number of real world network data sets for different statistical tasks, including community detection with and without edge covariates, and network assisted learning.
A Model of Fake Data in Data-driven Analysis
http://jmlr.org/papers/v21/17-360.html
2020Xiaofan Li, Andrew B. Whinston
Data-driven analysis has been increasingly used in various decision making processes. With more sources, including reviews, news, and pictures, can now be used for data analysis, the authenticity of data sources is in doubt. While previous literature attempted to detect fake data piece by piece, in the current work, we try to capture the fake data sender's strategic behavior to detect the fake data source. Specifically, we model the tension between a data receiver who makes data-driven decisions and a fake data sender who benefits from misleading the receiver. We propose a potentially infinite horizon continuous time game-theoretic model with asymmetric information to capture the fact that the receiver does not initially know the existence of fake data and learns about it during the course of the game. We use point processes to model the data traffic, where each piece of data can occur at any discrete moment in a continuous time flow. We fully solve the model and employ numerical examples to illustrate the players' strategies and payoffs for insights. Specifically, our results show that maintaining some suspicion about the data sources and understanding that the sender can be strategic are very helpful to the data receiver. In addition, based on our model, we propose a methodology of detecting fake data that is complementary to the previous studies on this topic, which suggested various approaches on analyzing the data piece by piece. We show that after analyzing each piece of data, understanding a source by looking at the its whole history of pushing data can be helpful.
A Statistical Learning Approach to Modal Regression
http://jmlr.org/papers/v21/17-068.html
2020Yunlong Feng, Jun Fan, Johan A.K. Suykens
This paper studies the nonparametric modal regression problem systematically from a statistical learning viewpoint. Originally motivated by pursuing a theoretical understanding of the maximum correntropy criterion based regression (MCCR), our study reveals that MCCR with a tending-to-zero scale parameter is essentially modal regression. We show that the nonparametric modal regression problem can be approached via the classical empirical risk minimization. Some efforts are then made to develop a framework for analyzing and implementing modal regression. For instance, the modal regression function is described, the modal regression risk is defined explicitly and its Bayes rule is characterized; for the sake of computational tractability, the surrogate modal regression risk, which is termed as the generalization risk in our study, is introduced. On the theoretical side, the excess modal regression risk, the excess generalization risk, the function estimation error, and the relations among the above three quantities are studied rigorously. It turns out that under mild conditions, function estimation consistency and convergence may be pursued in modal regression as in vanilla regression protocols such as mean regression, median regression, and quantile regression. On the practical side, the implementation issues of modal regression including the computational algorithm and the selection of the tuning parameters are discussed. Numerical validations on modal regression are also conducted to verify our findings.
A Low Complexity Algorithm with O(√T) Regret and O(1) Constraint Violations for Online Convex Optimization with Long Term Constraints
http://jmlr.org/papers/v21/16-494.html
2020Hao Yu, Michael J. Neely
This paper considers online convex optimization over a complicated constraint set, which typically consists of multiple functional constraints and a set constraint. The conventional online projection algorithm (Zinkevich, 2003) can be difficult to implement due to the potentially high computation complexity of the projection operation. In this paper, we relax the functional constraints by allowing them to be violated at each round but still requiring them to be satisfied in the long term. This type of relaxed online convex optimization (with long term constraints) was first considered in Mahdavi et al. (2012). That prior work proposes an algorithm to achieve $O(\sqrt{T})$ regret and $O(T^{3/4})$ constraint violations for general problems and another algorithm to achieve an $O(T^{2/3})$ bound for both regret and constraint violations when the constraint set can be described by a finite number of linear constraints. A recent extension in Jenatton et al. (2016) can achieve $O(T^{\max\{\theta,1-\theta\}})$ regret and $O(T^{1-\theta/2})$ constraint violations where $\theta\in (0,1)$. The current paper proposes a new simple algorithm that yields improved performance in comparison to prior works. The new algorithm achieves an $O(\sqrt{T})$ regret bound with $O(1)$ constraint violations.