I am a researcher with expertise in machine learning, neural networks, optimization, large-scale learning and statistical modeling in general. I am now at Microsoft Research in Montreal and an adjunct faculty at both McGill and UdeM. I am a co-recipient of the 2018 Lagrange prize with Francis Bach and Mark Schmidt.
My two main interests at the moment are: Understanding how the interplay between noise and curvature affects convergence speed and generalization in stochastic optimization. Understanding the dynamics of optimization in reinforcement learning, especially policy-gradient methods.
Besides purely technical topics, I am also interested in team management and organization, and in particular how to effectively address stress, ensure well-being and achieve a truly inclusive environment in research.