From Monte Carlo to Las Vegas: Improving Restricted Boltzmann Machine Training Through Stopping Sets

Authors

  • Pedro Savarese Toyota Technical Institute at Chicago
  • Mayank Kakodkar Purdue University, West Lafayette, IN
  • Bruno Ribeiro Purdue University, West Lafayette, IN

Keywords:

ML: Deep Learning/Neural Networks, ML: Unsupervised Learning

Abstract

We propose a Las Vegas transformation of Markov Chain Monte Carlo (MCMC) estimators of Restricted Boltzmann Machines (RBMs). We denote our approach Markov Chain Las Vegas (MCLV). MCLV gives statistical guarantees in exchange for random running times. MCLV uses a stopping set built from the training data and has maximum number of Markov chain steps K (referred as MCLV-K). We present a MCLV-K gradient estimator (LVS-K) for RBMs and explore the correspondence and differences between LVS-K and Contrastive Divergence (CD-K), with LVS-K significantly outperforming CD-K training RBMs over the MNIST dataset, indicating MCLV to be a promising direction in learning generative models.

Downloads

Published

2018-04-29

How to Cite

Savarese, P., Kakodkar, M., & Ribeiro, B. (2018). From Monte Carlo to Las Vegas: Improving Restricted Boltzmann Machine Training Through Stopping Sets. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11821