Pascal is a Professor in the David R. Cheriton School of Computer Science at the University of Waterloo. He served as Research Director and Principal Research Scientist at the Waterloo Borealis AI Research Lab funded by the Royal Bank of Canada (2018-2020). His research focuses on reinforcement learning and machine learning more generally with application to natural language processing, sports analytics and material design. He is most well known for his contributions to the development of Reinforcement Learning algorithms. Notable projects that his research team are currently working on include probabilistic deep learning, robust machine learning, data efficient reinforcement learning, conversational agents, automated document editing, adaptive satisfiability and knowledge graphs. Pascal completed his PhD in Computer Science at the University of Toronto, his Master’s degree at the University of British Columbia and undergraduate degree at McGill University. Pascal served as scientific advisor for ElementAI, DialPad, ProNavigator, Scribendi and his research collaborators also include Google, Microsoft, Intel, Ford, Manulife, Royal Bank of Canada, Bank of Montreal, Kik Interactive, In the Chat, Slyce, HockeyTech, the Alzheimer Association, the UW-Schlegel Research Institute for Aging, Sunnybrook Health Science Centre and the Toronto Rehabilitation Institute.
Professor, David R. Cheriton School of Computer Science, University of Waterloo
Canada CIFAR Artificial Intelligence Chair
Member, Waterloo Artificial Intelligence Institute
Research Interests
- Machine Learning and Probabilistic Models
- Natural Language Processing
- Material Design
Highlights
- David R. Cheriton Faculty Fellowship (2015-2018)
- Runner up best student paper award (SAT-2017)
- Best main track solver and best application solver (SAT-2016 Competition)
- Best paper award runner-up (UAI-2008)
- Ontario Early Researcher Award (2008-2013)
Publications
Optimality and stability in non-convex smooth games
2022
Quantifying and Improving Transferability in Domain Generalization
2021
Linearizing Contextual Bandits with Latent State Dynamics
2022
Learning Functions on Multiple Sets using Multi-Set Transformers
2022
System and method for bi-directional translation using sum-product networks
2021
Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning
2021
Decentralized Mean Field Games
2021
Learning Object-Oriented Dynamics for Planning from Text
2021
Distributional Reinforcement Learning with Monotonic Splines
2021
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation
2021
Partially Observable Mean Field Reinforcement Learning
2021
Attribute controlled dialogue prompting
2023
Contrastive Deterministic Autoencoders For Language Modeling
2023
Calibrated one round federated learning with bayesian inference in the predictive space
2024
Multi-Modal Inverse Constrained Reinforcement Learning from a Mixture of Demonstrations
2023
An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient
2023
Batchnorm Allows Unsupervised Radial Attacks
2023
Do we need Label Regularization to Fine-tune Pretrained Language Models?
2023