This is a navigation window which overlays the main content of the page. Pressing the "X" at the top right corner of the modal will close the modal and bring you back to where you were on the page.
See posts about
This is a call to action window which overlays the main content of the page. Pressing the "X" at the top right corner of the modal will close the modal and bring you back to where you were on the page.
Let's Collaborate
This is a search window which overlays the main content of the page. Pressing the "X" at the top right corner of the modal will close the modal and bring you back to where you were on the page.
Associate Professor, Department of Statistical Sciences, Faculty of Arts & Science, University of Toronto
Associate Professor, Department of Computer and Mathematical Sciences, University of Toronto Scarborough
Canada CIFAR Artificial Intelligence Chair
Roy’s research in deep learning spans theory and practice. His contributions range from his pioneering work on empirically grounded statistical theory for deep learning, to state-of-the-art algorithms for neural network compression and data-parallel training. His experimental work has shed light on various deep learning phenomena, including neural network training dynamics and linear mode connectivity, while his recent theoretical work introduces simple but accurate mathematical models for deep neural networks at initialization.
Beyond his contributions to deep learning, Roy has made significant advances to the mathematical and statistical underpinnings of AI. His dissertation on probabilistic programming languages and computable probability theory was recognized by an MIT Sprowls Award. Roy recently resolved several open problems in statistical decision theory posed over 70 years ago, by exploiting the properties of infinitesimal numbers to expand the set of allowable Bayesian priors. His latest work, focussing on robust and adaptive decision making, has been recognized by multiple oral presentations at leading conferences and best poster awards.
Research Interests
Foundations of Machine Learning
Deep Learning
Sequential Decision Making
Statistical Learning Theory
Probabilistic Programming
Bayesian-Frequentist Interface
PAC-Bayes
Publications
Data-dependent PAC-Bayes priors via differential privacy
G. K. Dziugaite, and D. M. Roy
Advances in Neural Information Processing Systems 31 2018
On the computability of conditional probability
N. L. Ackerman, C. E. Freer, and D. M. Roy
Journal of the ACM 2019 66(3)
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
G. K. Dziugaite, and D. M. Roy
Proceedings of the 35th International Conference on Machine Learning (ICML) 2018
An estimator for the tail-index of graphex processes
Z. Naulet, E. Sharma, V. Veitch, and D. M. Roy
2017
Sampling and estimation for (sparse) exchangeable graphs
V. Veitch, and D. M. Roy
Ann. Statist. 2019 47(6):3274--3299
On extended admissible procedures and their nonstandard Bayes risk
Haosui Duanmu and Daniel M Roy
2021
Towards a Unified Information-Theoretic Framework for Generalization
Mahdi Haghifam and Gintare Karolina Dziugaite and Shay Moran and Dan Roy
2021
The future is log-Gaussian: ResNets and their infinite-depth-and-width limit at initialization
Mufan Li and Mihai Nica and Dan Roy
2021
Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers
Jeffrey Negrea and Blair Bilodeau and Nicolò Campolongo and Francesco Orabona and Dan Roy
2021
Methods and Analysis of The First Competition in Predicting Generalization of Deep Learning
Yiding Jiang and Parth Natekar and Manik Sharma and Sumukh K Aithal and Dhruva Kashyap and Natarajan Subramanyam and Carlos Lassance and Daniel M Roy and Gintare Karolina Dziugaite and Suriya Gunasekar and Isabelle Guyon and Pierre Foret and Scott Yak and Hossein Mobahi and Behnam Neyshabur and Samy Bengio
2021
Minimax rates for conditional density estimation via empirical entropy
Blair Bilodeau and Dylan J Foster and Daniel M Roy
2023
Existence of matching priors on compact spaces
Haosui Duanmu and Daniel M Roy and Aaron Smith
2023
Relaxing the iid assumption: Adaptively minimax optimal regret via root-entropic regularization
Blair Bilodeau and Jeffrey Negrea and Daniel M Roy
2023
Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization
Idan Attias and Gintare Karolina Dziugaite and Mahdi Haghifam and Roi Livni and Daniel M Roy
2024
Probabilistic programming interfaces for random graphs: Markov categories, graphons, and nominal sets
Nate Ackerman and Cameron E Freer and Younesse Kaddar and Jacek Karwowski and Sean Moss and Daniel Roy and Sam Staton and Hongseok Yang
We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.