Abstract
Machine learning algorithms are increasingly being deployed into environments in which they must interact with other strategic agents with potentially misaligned objectives. While the presence of these strategic interactions create new challenges for learning algorithms, they also give rise to new opportunities for algorithm design.
This talk will begin by highlighting a line of work showing the unintuitive behaviors that arise from the interplay between learning algorithms and strategic agents. First, it will be shown, both in theory and practice, how learning algorithms (even those built on top of large language models) are susceptible to the gaming of data by vanishing small groups of people, even if individuals have no effect on them in isolation. Eric will also present recent work on how strategic interactions can break out basic intuition that larger models, more data, and more compute always improves performance. The resulting phenomenon suggests that even when one has access to infinite data strategic interactions can make smaller and less expressive models yield better equilibrium outcomes. Then in conclusion, with some recent work on algorithm design in strategic environments in the context of multi-agent RL. In particular, this talk will show how to tweak deep Q learning to allow it to have strong convergence guarantees in competitive games.
Bio
Eric Mazumdar is an Assistant Professor in Computing and Mathematical Sciences and Economics at Caltech. 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. Eric is the recipient of a NSF Career Award and was a fellow of the Simons Institute for Theoretical Computer Science 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 and received his B.S. in Electrical Engineering and Computer Science at the Massachusetts Institute of Technology (MIT).
