Deep Exponential Families

Unsupervised, Generative Deep Learning
Mai 2015

Deep Exponential Families

Mai 2015

We describe deep exponential families (DEFs), a class of latent variable models that are inspired by the hidden structures used in deep neural networks. DEFs capture a hierarchy of dependencies between latent variables, and are easily generalized to many settings through exponential families. We perform inference using recent “black box” variational inference techniques. We then evaluate various DEFs on text and combine multiple DEFs into a model for pairwise recommendation data. In an extensive study, we show going beyond one layer improves predictions for DEFs. We demonstrate that DEFs find interesting exploratory structure in large data sets, and give better predictive performance than state-of-the-art models.

Reference

Rajesh Ranganath, Linpeng Tang, Laurent Charlin, David Blei, Deep Exponential Families, in: Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, pp. 762–771, 2015

Source code

Linked Profiles