Eric Mazumdar's research lies at the intersection of machine learning and economics. He is broadly interested in developing the tools and understanding necessary to confidently deploy machine learning algorithms into societal-scale systems. This requires understanding the theoretical underpinnings of learning algorithms in uncertain, dynamic environments where they must interact with other strategic agents, humans, and algorithms. Practically, he applies his work to work to problems in intelligent infrastructure, online markets, e-commerce, and the delivery of healthcare. Some of the topics addressed by his recent work include strategic classification, learning behavioral models of human decision-making from data, min-max optimization, learning in games, multi-agent reinforcement learning, distributionally robust learning, and learning for control.