Undirected Graphical Models as Approximate Posteriors

Arash Vahdat · Evgeny Andriyash · William Macready

Keywords: [ Approximate Inference ] [ Bayesian Methods ] [ Deep Generative Models ] [ Generative Models ] [ Probabilistic Inference - Approximate, Monte Carlo, and Spectral Methods ]

[ Abstract ] [ Join Zoom
Please do not share or post zoom links

Abstract:

The representation of the approximate posterior is a critical aspect of effective variational autoencoders (VAEs). Poor choices for the approximate posterior have a detrimental impact on the generative performance of VAEs due to the mismatch with the true posterior. We extend the class of posterior models that may be learned by using undirected graphical models. We develop an efficient method to train undirected approximate posteriors by showing that the gradient of the training objective with respect to the parameters of the undirected posterior can be computed by backpropagation through Markov chain Monte Carlo updates. We apply these gradient estimators for training discrete VAEs with Boltzmann machines as approximate posteriors and demonstrate that undirected models outperform previous results obtained using directed graphical models. Our implementation is publicly available.

Chat is not available.