Join us for an invited talk with Sinead Williamson, Assistant Professor in the Information, Risk, and Operations Management department of the McCombs School of Business at the University of Texas at Austin:

• Title: Parallelizing MCMC for Bayesian nonparametrics.
• Event Date: Thursday, November 20; 2014, 11:00 am.
• Location: 4.2.E04 Room; Torres Quevedo Building; Leganés Campus; Universidad Carlos III de Madrid.

Abstract:

Bayesian nonparametric models, such as those based on the Dirichlet process and the Pitman-Yor process, provide elegant and flexible alternatives to parametric models when the number of underlying components is unknown or growing. Unfortunately, inference in such models can be slow, and previous parallelization methods have relied on introducing approximations which can lead to inaccuracies in the posterior estimate. In this talk, I will construct auxiliary variable representations for the Dirichlet process, the Pitman-Yor process, and some hierarchical extensions, and show how these representations facilitate the development of distributed Markov chain Monte Carlo schemes that use the correct equilibrium distribution. Experimental analyses show that this approach allows scalable inference without the deterioration in estimate quality that accompanies existing methods.

Joint work with Avinava Dubey and Eric Xing.

Bio:

Sinead Williamson is an Assistant Professor in the Information, Risk, and Operations Management department of the McCombs School of Business at the University of Texas at Austin. She received her MEng from the University of Oxford, MSc from University College London, and Ph.D. from the University of Cambridge. Her main research areas are Bayesian nonparametric statistics and machine learning. Before joining the faculty at UT Austin, Sinead was a post doc at Carnegie Mellon University.