My recent work has focused on the theoretical foundations of online linear control and reinforcement learning, with past research ranging broadly across topics in adaptive sampling, multi-arm bandits, complexity of convex and non-convex optimization, and fairness in machine learning. I am particularly interested in transferring optimal “fast rates” familiar in statistical and online learning to more complex reinforcement learning settings, and, conversely, understanding when these improved bounds are unattainable. I'm also interested in characterizing optimal regret when the learner faces additional challenges, such as incomplete observation, corrupted information, and safety constraints.