Machine Learning Seminar

Feb 24

Wednesday, February 24, 2016

11:45 am - 1:45 pm
Gross Hall 330

Presenter

Rong Ge, Duke University

This week's Machine Learning Seminar Speaker is Rong Ge of Duke University Title: Towards provable algorithms for inference in topic models Abstract: Recently, there has been considerable progress on designing algorithms with provable guarantees for parameter learning in latent variable models. Designing provable algorithms for inference seems more difficult in many settings. In this talk I will describe a first step towards provable inference in topic models. We leverage a property of topic models that enables us to construct simple linear estimators for the unknown topic proportions that have small variance, and consequently can work with short documents. Our estimators also correspond to finding an estimate around which the posterior is well-concentrated. We show lower bounds that for shorter documents it can be information theoretically impossible to find the hidden topics. Finally, we give empirical results that demonstrate that our algorithm works on realistic topic models. It yields good solutions on synthetic data and runs in time comparable to a single iteration of Gibbs sampling. Bio: Rong Ge is a new faculty at Duke computer science department. He got his Ph.D. in Princeton University and was a post-doc at Microsoft Research New England before joining Duke. Rong Ge is broadly interested in theoretical computer science and machine learning, his research mostly focuses on designing algorithms with provable guarantees for machine learning problems.

Contact

Dawn, Ariel
613-0979
ariel.dawn@duke.edu