PhD Thesis: 'Computational Trade-offs in Statistical Learning', UC Berkeley, 2012
Co-authored a monograph on RL theory based on course notes with Nan Jiang and Sham Kakade
Published extensively in top-tier journals including Journal of Machine Learning Research, IEEE Transactions on Information Theory, The Annals of Statistics, and SIAM Journal on Optimization
Notable papers include: 'Model-free Representation Learning and Exploration in Low-rank MDPs', 'Federated Residual Learning', 'A Multiworld Testing Decision Service', 'On the Theory of Policy Gradient Methods', and 'Active Learning for Cost-Sensitive Classification'
Research contributions span contextual bandits, reinforcement learning, active learning, overcomplete dictionary recovery, stochastic convex optimization, and distributed optimization