The success of large language models is driven by the abundance and natural structure of data. What does this tell us about our universe and ourselves? How can we use these insights to advance applications in critical fields like drug discovery? Chris asks questions like these and is interested in building machine learning systems that learn in stubbornly complex settings relevant to medicine. He received the Corcoran Memorial Prize for his Oxford thesis and has received a number of paper awards at the top machine learning conferences. Chris is known for his gradient estimation techniques, which are now standard tools in the deep learning toolbox, and for his role as a founding member of the AlphaGo project, which was the first computer program to defeat a world champion in the game of Go.
Assistant Professor, Department of Computer Science, Faculty of Arts & Science, University of Toronto
Assistant Professor, Department of Statistical Sciences, Faculty of Arts & Science, University of Toronto
Canada CIFAR Artificial Intelligence Chair
Research Interests
- Scaling laws
- Machine learning
- AI in drug discovery
Highlights
- Open Philanthropy AI Fellow 2018
- NIPS Best Paper Award in 2014
- Founding members of the AlphaGo project
- Outstanding Paper Award Honorable Mention, ICML 2021
- Corcoran Memorial Prize (Thesis Award), Dept. of Statistics, Oxford 2020
- IJCAI Marvin Minsky Medal for Outstanding Achievements in AI 2018
- Breakthrough of the Year runner-up, Science 2016
- Cannes Lions International Festival of Creativity, Grand Prix 2016
Publications
Conditional neural processes
2018
On empirical comparisons of optimizers for deep learning
2019
Tighter variational bounds are not necessarily better
2017
Doubly reparameterized gradient estimators for Monte Carlo objectives
2018
Gradient Estimation with Stochastic Softmax Tricks
202
Hamiltonian descent for composite objectives
2019
Hamiltonian descent methods
2018
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
2018
Lossy Compression for Lossless Prediction
2021
Optimal Representations for Covariate Shift
2022
Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
2021
Selecting actions to be performed by a reinforcement learning agent using tree search
2021
Twisted variational sequential monte carlo
2018
Dual space preconditioning for gradient descent
2021
Learning to cut by looking ahead: Cutting plane selection via imitation learning
2022
Learning Generalized Gumbel-max Causal Mechanisms
2021
Augment with Care: Contrastive Learning for the Boolean Satisfiability Problem
2022
Learning Branching Heuristics for Propositional Model Counting
2021
Direct policy gradients: Direct optimization of policies in discrete action spaces
2020
Neural network systems implementing conditional neural processes for efficient learning
2021
The machine learning for combinatorial optimization competition (ml4co): Results and insights
2022
Unbiased gradient estimation with balanced assignments for mixtures of experts
2021
Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions
2023
Bayesian nonparametrics for offline skill discovery
2022
Stochastic Reweighted Gradient Descent
2022
Learning to Extend Program Graphs to Work-in-Progress Code
2021
Training a policy neural network and a value neural network
2018
Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator
2021
Probabilistic invariant learning with randomized linear classifiers
2023
Identifying the risks of lm agents with an lm-emulated sandbox
2024
Observational Scaling Laws and the Predictability of Language Model Performance
2024
End-To-End Causal Effect Estimation from Unstructured Natural Language Data
2024
Experts Don’t Cheat: Learning What You Don’t Know By Predicting Pairs
2024