Department of Engineering

Dr D. M. Roy

Newton Fellow
Computational and Biological Learning Lab
Information Engineering Division

My research interests lie at the intersection of computer science, statistics and probability theory; I study probabilistic programming languages to develop computational perspectives on fundamental ideas in probability theory and statistics. I am particularly interested in the use of recursion to define nonparametric distributions on data structures; representation theorems that connect computability and probabilistic structures; and the complexity of inference.

Please see my permanent website (danroy.org) for more information.

Representative papers (see also danroy.org dan roy daniel roy)

• On the computability of conditional probability
  (with Nate Ackerman and Cameron Freer)
• Computable de Finetti measures
  (with Cameron Freer)
• Posterior distributions are computable from predictive distributions
  (with Cameron Freer)
• Complexity of Inference in Topic Models
  (with David Sontag)
• Computable exchangeable sequences have computable de Finetti measures
  (with Cameron Freer)
• The Mondrian Process
  (with Yee Whye Teh)
• A stochastic programming perspective on nonparametric Bayes
  (with Vikash Mansinghka, Noah Goodman and Joshua Tenenbaum)
• Church: a language for generative models
  (with Noah Goodman, Vikash Mansinghka, Keith Bonawitz and Joshua Tenenbaum)
• Bayesian Agglomerative Clustering with Coalescents
  (with Yee Whye Teh and Hal Daume)

Contact Information