Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends

[edit]

Christopher Tosh ;
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:840-849, 2016.

Abstract

Alternating Gibbs sampling is a modification of classical Gibbs sampling where several variables are simultaneously sampled from their joint conditional distribution. In this work, we investigate the mixing rate of alternating Gibbs sampling with a particular emphasis on Restricted Boltzmann Machines (RBMs) and variants.

Related Material