Relaxations for inference in restricted Boltzmann machines
Machine Learning
2014-01-03 v2 Machine Learning
Abstract
We propose a relaxation-based approximate inference algorithm that samples near-MAP configurations of a binary pairwise Markov random field. We experiment on MAP inference tasks in several restricted Boltzmann machines. We also use our underlying sampler to estimate the log-partition function of restricted Boltzmann machines and compare against other sampling-based methods.
Cite
@article{arxiv.1312.6205,
title = {Relaxations for inference in restricted Boltzmann machines},
author = {Sida I. Wang and Roy Frostig and Percy Liang and Christopher D. Manning},
journal= {arXiv preprint arXiv:1312.6205},
year = {2014}
}
Comments
ICLR 2014 workshop track submission