Speaker: Daniel Roy, Emmanuel College, University of Cambridge
Location: Warren Weaver Hall 1302
Date: March 31, 2014, 11:30 a.m.
Host: Denis Zorin
The complexity, scale, and variety of data have grown enormously, and present exciting opportunities for new applications. Just as high-level programming languages and compilers empowered experts to solve computational problems more quickly, and made it possible for nonexperts to solve them at all, a number of high-level probabilistic programming languages with computationally-universal inference engines have been developed with the potential to similarly transform the practice of Bayesian statistics. These systems provide formal languages for specifying probabilistic models compositionally, and general algorithms for turning these specifications into efficient algorithms for inference.
In this talk, I will address three key questions at the theoretical and algorithmic foundations of probabilistic programming---and probabilistic modeling more generally---that can be answered using tools from probability theory, computability and complexity theory, and nonparametric Bayesian statistics. Which Bayesian inference problems can be automated, and which cannot? Can probabilistic programming languages represent the stochastic processes at the core of state-of-the-art nonparametric Bayesian models? And if not, can we construct useful approximations? I’ll close by relating these questions to other challenges and opportunities ahead at the intersections of computer science, statistics, and probability.
Daniel Roy is a Research Fellow of Emmanuel College, University of Cambridge, and a member of the Machine Learning Group in the Department of Engineering. Daniel earned his SB, MEng, and PhD in Computer Science from MIT, and subsequently held a Newton International Fellowship of the Royal Society. In 2011, Daniel was named a recipient of a George M. Sprowls Award, which is awarded for the best doctoral theses in computer science at MIT.
Refreshments will be offered starting 15 minutes prior to the scheduled start of the talk.