Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines
Guillaume Desjardins, Aaron Courville, Yoshua Bengio, Pascal Vincent, Olivier Delalleau ; JMLR W&CP 9:145-152, 2010.
Alternating Gibbs sampling is the most common scheme used for sampling from Restricted Boltzmann Machines (RBM), a crucial component in deep architectures such as Deep Belief Networks. However, we find that it often does a very poor job of rendering the diversity of modes captured by the trained model. We suspect that this hinders the advantage that could in principle be brought by training algorithms relying on Gibbs sampling for uncovering spurious modes, such as the Persistent Contrastive Divergence algorithm. To alleviate this problem, we explore the use of tempered Markov Chain Monte-Carlo for sampling in RBMs. We find both through visualization of samples and measures of likelihood on a toy dataset that it helps both sampling and learning.