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.
Matthew Hoffman (Google Research)
Related Events (a corresponding poster, oral, or spotlight)
2017 Talk: Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo »
Mon Aug 7th 06:06 -- 06:24 AM Room Parkside 1