Assistant Professor at McGill University, Adjunct Professor at University of Montréal, Core Academic Member at MILA, Canada CIFAR AI (CCAI) Chair holder

The widespread adoption of deep learning is often attributed to its automatic feature construction with minimal inductive bias. However, in many real-world tasks, the learned function is intended...

The growing utilization of machine learning (ML) in decision-making processes raises questions about its benefits to society. In this study, we identify and analyze three axes of heterogeneity...

We are interested in PETs/PPTs that minimize data exposure and limit its purpose, while enabling a range of products and use cases (e.g., Ads, Messaging, etc). These technologies enable us to offer...