Daniel is now an Assistant Professor in the Department of Statistical Sciences at the University of Toronto.
Daniel joined the group in March 2011 as a Newton Fellow, having just completed his Ph.D. in Computer Science at MIT. Daniel’s research interests lie at the intersection of computer science, statistics and probability theory. His recent work addresses several theoretical questions at the foundation of the emerging field of probabilistic programming in AI and machine learning. At Cambridge, he has continued to pursue his interests in the complexity of probabilistic inference; representation theorems connecting complexity and probabilistic structures; and the use of recursion to define nonparametric distributions on data structures.
Complexity of Inference in Latent Dirichlet Allocation
David Sontag and Daniel Roy
Adv. Neural Information Processing Systems 23 (NIPS), 2012.
Computable de Finetti measures
(with Cameron Freer)
Annals of Pure and Applied Logic, 2011.
Noncomputable conditional distributions
(with Nate Ackerman and Cameron Freer)
Proc. Logic in Computer Science (LICS), 2011.
Computability, inference and modeling in probabilistic programming
Ph.D. thesis, Massachusetts Institute of Technology, 2011. MIT/EECS George M. Sprowls Doctoral Dissertation Award
For more information, and a list of recent publications, see Daniel’s homepage.