Eric V. Mazumdar

Eric V. Mazumdar is an Assistant Professor of Computing and Mathematical Sciences and Economics at the California Institute of Technology. His research focuses on the intersection of machine learning and economics, with an emphasis on developing tools and understanding for deploying machine learning algorithms in societal-scale systems. His work addresses topics such as strategic classification, learning behavioral models of human decision-making, min-max optimization, and learning in games. Mazumdar's research has practical applications in intelligent infrastructure, online markets, e-commerce, and healthcare. He is affiliated with the CS department at Caltech and teaches courses related to networks, learning, and control systems.

Eric Mazumdar is an Assistant Professor at the California Institute of Technology, specializing in the intersection of game theory, machine learning, and optimization. His research focuses on understanding the dynamics of strategic interactions in multi-agent systems, with an emphasis on convergence guarantees, equilibrium analysis, and algorithmic design. He explores topics such as gradient-based learning in continuous games, Nash equilibria in zero-sum games, and reinforcement learning for uncertain systems. His work also addresses challenges in strategic classification, contextual bandits, and robust multi-agent learning. Mazumdar's contributions aim to advance the theoretical foundations of learning in strategic environments.