Home Page

Papers

Submissions

News

Editorial Board

Announcements

Proceedings

Open Source Software

Search

Login



RSS Feed

Convex Risk Minimization and Conditional Probability Estimation

Matus Telgarsky, Miroslav Dudík, Robert Schapire
Proceedings of The 28th Conference on Learning Theory, pp. 1629–1682, 2015

Abstract

This paper proves, in very general settings, that convex risk minimization is a procedure to select a unique conditional probability model determined by the classification problem. Unlike most previous work, we give results that are general enough to include cases in which no minimum exists, as occurs typically, for instance, with standard boosting algorithms. Concretely, we first show that any sequence of predictors minimizing convex risk over the source distribution will converge to this unique model when the class of predictors is linear (but potentially of infinite dimension). Secondly, we show the same result holds for empirical risk minimization whenever this class of predictors is finite dimensional, where the essential technical contribution is a norm-free generalization bound.

Related Material