Daniel Roy - Vector Institute for Artificial Intelligence

Research Interests

Foundations of machine learning
Statistical learning theory
Neural networks
Probabilistic programming
Bayesian-frequentist interface
PAC-Bayes
Computability

Biography

Daniel’s research blends computer science, statistics and probability theory; He studies “probabilistic programming” and develop computational perspectives on fundamental ideas in probability theory and statistics. Daniel is particularly interested in: representation theorems that connect computability, complexity, and probabilistic structures; stochastic processes, the use of recursion to define stochastic processes, and applications to nonparametric Bayesian statistics; and the complexity of probabilistic and statistical inference, especially in the context of probabilistic programming. Ultimately, Daniel is motivated by the long term goal of making lasting contributions to our understanding of complex adaptive systems and especially Artificial Intelligence.

Highlights

Ontario Early Researcher Award
Google Faculty Research Award
Connaught New Researcher Award
Newton International Fellowship, Royal Academy of Engineering
Research Fellowship, Emmanuel College
MIT George M. Sprowls Doctoral Dissertation Award
Siebel Scholarship

Selected Papers

Data-dependent PAC-Bayes priors via differential privacyGintare Karolina Dziugaite and Daniel M. Roy https://arxiv.org/abs/1802.09583
On the computability of graphons (with Nathanael L. Ackerman, Jeremy Avigad, Cameron E. Freer, and Jason M. Rute) https://arxiv.org/abs/1801.10387
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors Gintare Karolina Dziugaite and Daniel M. Roy https://arxiv.org/abs/1712.09376
An estimator for the tail-index of graphex processes Zacharie Naulet, Ekansh Sharma, Victor Veitch, Daniel M. Roy https://arxiv.org/abs/1712.01745
On Extended Admissible Procedures and their Nonstandard Bayes Risk Haosui Duanmu and Daniel M. Roy https://arxiv.org/abs/1612.09305
Sampling and Estimation for (Sparse) Exchangeable Graphs Victor Veitch and Daniel M. Roy https://arxiv.org/abs/1611.00843
The Class of Random Graphs Arising from Exchangeable Random Measures Victor Veitch and Daniel M. Roy https://arxiv.org/abs/1512.03099
Sequential Monte Carlo as Approximate Sampling: bounds, adaptative resampling via \infty-ESS, and an application to Particle Gibbs (with Jonathan Huggins) To appear in Bernoulli. http://arxiv.org/abs/1503.00966
Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data Gintare Karolina Dziugaite and Daniel M. Roy In Proc. Uncertainty in Artificial Intelligence (UAI), 2017. https://arxiv.org/abs/1703.11008
On computability and disintegration (with Nate Ackerman and Cameron Freer) In Mathematical Structures in Computer Science. https://arxiv.org/abs/1509.02992