Skip to yearly menu bar Skip to main content


Poster

Neural Variational Inference and Learning in Undirected Graphical Models

Volodymyr Kuleshov · Stefano Ermon

Pacific Ballroom #108

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


Abstract:

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.

Live content is unavailable. Log in and register to view live content