Title: Learning & Decision-Making in Societal Systems: Theory, Algorithms, and Design.

Abstract: The ability to learn from data and make decisions in real-time has led to the rapid deployment of machine learning algorithms across many aspects of everyday life. Despite their potential to enable new services and address persistent societal issues, the widespread use of these algorithms has led to unintended consequences like flash crashes in financial markets or price collusion on e-commerce platforms. These consequences are the inevitable result of deploying algorithms--- that were  designed to operate in isolation---  in uncertain dynamic environments in which they interact with other autonomous agents, algorithms, and human decision makers.

To address these issues, it is necessary to develop an understanding of the fundamental limits of learning algorithms in societal-scale systems. In this talk, I will give an overview of my work on three aspects of learning and decision-making in societal-scale systems:  (i) Bayesian decision-making with approximate inference, (ii) Understanding why and when learning algorithms fail in game theoretic settings, and (iii) Understanding the dynamics of strategic interactions.

Bio: Eric Mazumdar is an Assistant Professor in Computing and Mathematical Sciences and Economics at Caltech, and currently a Research Fellow at the Simons Institute for the semester on Learning in Games. He obtained his Ph.D in Electrical Engineering and Computer Science at UC Berkeley where he was advised by Michael Jordan and Shankar Sastry. Prior to Berkeley, he received a B.S. in Electrical Engineering and Computer Science at MIT. His research lies at the intersection of machine learning and economics where he is broadly interested in developing the tools and understanding necessary to confidently deploy machine learning algorithms into societal-scale systems. He applies his work to problems in intelligent infrastructure, online markets, e-commerce, and the delivery of healthcare.