ICML 2017poster132 citations
Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo
Abstract
Deep latent Gaussian models are powerful and popular probabilistic models of high-dimensional data. These models are almost always fit using variational expectation-maximization, an approximation to true maximum-marginal-likelihood estimation. In this paper, we propose a different approach: rather than use a variational approximation (which produces biased gradient signals), we use Markov chain Monte Carlo (MCMC, which allows us to trade bias for computation). We find that our MCMC-based approach has several advantages: it yields higher held-out likelihoods, produces sharper images, and does not suffer from the variational overpruning effect. MCMC’s additional computational overhead proves to be significant, but not prohibitive.
BibTeX
@InProceedings{pmlr-v70-hoffman17a,
title = {Learning Deep Latent {G}aussian Models with {M}arkov Chain {M}onte {C}arlo},
author = {Matthew D. Hoffman},
booktitle = {Proceedings of the 34th International Conference on Machine Learning},
pages = {1510--1519},
year = {2017},
editor = {Precup, Doina and Teh, Yee Whye},
volume = {70},
series = {Proceedings of Machine Learning Research},
month = {06--11 Aug},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v70/hoffman17a/hoffman17a.pdf},
url = {https://proceedings.mlr.press/v70/hoffman17a.html},
abstract = {Deep latent Gaussian models are powerful and popular probabilistic models of high-dimensional data. These models are almost always fit using variational expectation-maximization, an approximation to true maximum-marginal-likelihood estimation. In this paper, we propose a different approach: rather than use a variational approximation (which produces biased gradient signals), we use Markov chain Monte Carlo (MCMC, which allows us to trade bias for computation). We find that our MCMC-based approach has several advantages: it yields higher held-out likelihoods, produces sharper images, and does not suffer from the variational overpruning effect. MCMC’s additional computational overhead proves to be significant, but not prohibitive.}
}