Preference and Participation Dynamics in Learning Systems (via Zoom)

Abstract: When machine learning models are deployed, they can affect the distribution on which they operate. Such endogenous distribution shifts arise due to the impact of decisions on individuals. In this talk, I will discuss models of impact in two settings: biased-assimilation preference dynamics in personalized recommendation, and participation dynamics in the presence of multiple learners. Based on joint work with Mihaela Curmei, Maryam Fazel, Jamie Morgenstern, and Lillian Ratliff.

Bio: 
Sarah is an Assistant Professor in the Computer Science Department at Cornell. She recently completed a PhD in EECS from UC Berkeley and was a postdoc at the University of Washington. Sarah is interested in the interplay between optimization, machine learning, and dynamics, and her research focuses on understanding the fundamentals of data-driven control and decision-making. This work is grounded in and inspired by applications ranging from robotics to recommendation systems.