Published papers include but are not limited to: 'No-Regret Incentive-Compatible Online Learning', 'Data-dependent Bounds with T-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching', etc., covering a wide range of topics such as online learning, multi-armed bandits, distributionally robust optimization, and more, published in top conferences like EC, COLT, ICML, AISTATS, NeurIPS, etc.
Research Experience
Currently an Associate Professor in the Department of Computer Science at the University of Victoria. Previously a postdoc at CWI (Amsterdam) and the Australian National University (Canberra).
Education
PhD: College of Computing at Georgia Tech, Advisor: Alex Gray; Postdoc: CWI in Amsterdam (with Peter Grünwald); Australian National University in Canberra (with Bob Williamson).
Background
Research focuses on developing and analyzing theoretically-principled methods for machine learning. Specifically interested in online learning/sequential prediction (prediction with expert advice, multi-armed bandits, reinforcement learning theory), statistical learning theory (empirical process theory, PAC-Bayesian methods), and transfer learning (especially lifelong learning and principled methods of transferring representations). Recently, interested in problems of learning in the presence of self-interested agents.