Roger is an Assistant Professor of Computer Science at the University of Toronto, focusing on machine learning. Previously, he was a postdoc at the University of Toronto, after having received a Ph.D. at MIT, studying under Bill Freeman and Josh Tenenbaum. Before that, Roger did his undergraduate degree in symbolic systems and MS in computer science at Stanford University. Roger is a co-creator of Metacademy, a web site which uses a dependency graph of concepts to help you formulate personalized learning plans for machine learning and related topics.
Faculty Member
Associate Professor, Department Computer Science, University of Toronto
Canada CIFAR Artificial Intelligence Chair
Research Interests
- AI Alignment
- Understanding Deep Learning
- Efficient Second-Order Approximations for Neural Nets
Highlights
- Alfred P. Sloan Research Fellow in Computer Science
- Connaught New Researcher Award
- Canada Research Chair in Probabilistic Inference and Deep Learning
- Canada CIFAR AI Chair
Publications
Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
International Conference on Learning Representations (ICLR) 2018
Understanding Short-Horizon Bias in Stochastic Meta-Optimization
International Conference on Learning Representations (ICLR) 2018
Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation
Advances in Neural Information Processing Systems (NIPS) 2017
The reversible residual network: Backpropagation without storing activations
Advances in Neural Information Processing Systems (NIPS) 2017
Lime: Learning inductive bias for primitives of mathematical reasoning
2021
Differentiable annealed importance sampling and the perils of gradient noise
2021
On Monotonic Linear Interpolation of Neural Network Parameters
2021
REFACTOR: Learning to Extract Theorems from Proofs
2021
Improving Mutual Information Estimation with Annealed and Energy-Based Bounds
2021