Rate My Professor Eric Mazumdar

Eric Mazumdar is an Assistant Professor of Computing and Mathematical Sciences and Economics at the California Institute of Technology (Caltech), contributing to the Computer Science faculty. His 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 work examines the theoretical underpinnings of learning algorithms in uncertain, dynamic environments where they interact with strategic agents, humans, and other algorithms. Practical applications span intelligent infrastructure, online markets, e-commerce, and healthcare delivery. Key topics 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. Mazumdar pursues principled approaches to algorithm design for strategic and dynamic environments, encompassing foundations for robust and resilient learning, scalable architectures and algorithms, and broader implications of algorithmic decision-making in society.