I'm broadly interested in theory and algorithms for machine learning. My Ph.D. work has focused on optimization and regret minimization in stateful environments, through lines of work on learning in dynamical systems and large-scale optimization. Recently, I've been applying these ideas to reinforcement learning, natural language processing, and time-series forecasting.
Before that, I completed a B.S. in Computer Science at Yale, where I worked on Laplacian solvers and exoplanets. I grew up in Toronto, and was an olympiad coder in a past life.