[Colloquium] Talk at TTIC: Daniel Roy, University of Cambridge

[Dawn Ellis]

When:     Monday, February 10th at 11am

Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room #526

Who:       Daniel Roy, Research Fellow of Emmanuel College, University of
Cambridge

Title:       Computational foundations of Bayesian inference and
probabilistic
              programming

Abstract:

The complexity, scale, and variety of data sets we now have access to 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
non-experts 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.

Bio:

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 received an SB, MEng, and PhD in Computer Science from
MIT, and subsequently held a Newton Fellowship of the Royal Society.  His
PhD dissertation on computability, inference, and modeling in probabilistic
programming won a 2011 MIT George M. Sprowls dissertation award in computer
science.

Host:  Greg Shakhnarovich, greg at ttic.edu


-- 
*Dawn Ellis*
Administrative Coordinator,
Bookkeeper
773-834-1757
dellis at ttic.edu

TTIC
6045 S. Kenwood Ave.
Chicago, IL. 60637
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20140204/cb1ff86a/attachment.htm