Rajesh Ranganath will present his Pre-FPO on Monday, October 31, 2016 at 11:15am in CS 401.

The members of his committee are as follows: David Blei (adviser), Sanjeev Arora, Barbara Englehardt, and Peter Orbanz (Columbia Univ.)  Title and Abstract follow below.

Title: Black Box Variational Inference and Deep Generative Models

Abstract: To model data we desire to express assumptions, infer hidden structure, make predictions, and simulate new data. Probabilistic generative models provide a common toolkit to meet these challenges. In this talk, I will discuss deep exponential families (DEFs). DEFs are a class of latent variable models  built from exponential families inspired by the hidden structure used in deep neural networks. We show results on text, and we show how to compose DEFs to build a model for pairwise recommendations.
Key to working with probabilistic generative models is computing the posterior: a typically tedious task. In the second half of the talk, I will present black box variational inference, a method to approximate the posterior with minimal model-specific analysis. This family of generic inference algorithms makes approximating the posterior of deep exponential families and other models possible.