Poster
Neural Variational Inference and Learning in Undirected Graphical Models
Volodymyr Kuleshov · Stefano Ermon

Mon Dec 4th 06:30 -- 10:30 PM @ Pacific Ballroom #108 #None
in Posters Mon »

Many problems in machine learning are naturally expressed in the language of undirected graphical models. Here, we propose black-box learning and inference algorithms for undirected models that optimize a variational approximation to the log-likelihood of the model. Central to our approach is an upper bound on the log-partition function parametrized by a function q that we express as a flexible neural network. Our bound makes it possible to track the partition function during learning, to speed-up sampling, and to train a broad class of hybrid directed/undirected models via a unified variational inference framework. We empirically demonstrate the effectiveness of our method on several popular generative modeling datasets.

Keywords: Variational Inference · Efficient Training Methods · Graphical Models · Efficient Inference Methods · Latent Variable Models · Generative Models

Author Information

Volodymyr Kuleshov (Stanford University / Afresh)
Stefano Ermon (Stanford)

More from the Same Authors