Timezone: »

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

Mon Dec 06:30 PM -- 10:30 PM PST @ Pacific Ballroom #108 #None

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.

Author Information

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

More from the Same Authors