November 21
@
12:00 PM
–
1:00 PM
UW-ISyE looks forward to welcoming Roy Dong Assistant Professor in the Industrial & Enterprise Systems Engineering department at the University of Illinois at Urbana-Champaign.
Roy Dong – research assistant professor, electrical and computer engineering
As data-driven methods are deployed in real-world settings, the processes that generate the observed data will often react to the decisions of the learner. For example, a data source may have some incentive for the algorithm to provide a particular label (e.g. approve a bank loan), and manipulate their features accordingly. In this talk, I will present our recent work on analyzing this decision-dependent distribution shift through the lens of perturbation analysis in control theory. This framework allows us to consider settings with multiple equilibria and characterize the regions of attraction for each equilibrium, which is observed in practice: learning algorithms can settle into echo chambers, and characterizes the set of initial conditions which leads to each ultimate outcome. Additionally, I will discuss how these methods can be computationally calculated using integral quadratic constraints, how they can be made distributionally robust, and how it can be used for trajectory predictions for robotic crowd navigation.
Bio: Roy Dong is an Assistant Professor in the Industrial & Enterprise Systems Engineering department at the University of Illinois at Urbana-Champaign. He received a BS Honors in Computer Engineering and a BS Honors in Economics from Michigan State University in 2010. He received a PhD in Electrical Engineering and Computer Sciences at the University of California, Berkeley in 2017, where he was funded in part by the NSF Graduate Research Fellowship. Prior to his current position, he was a postdoctoral researcher in the Berkeley Energy & Climate Institute, a visiting lecturer in the Industrial Engineering and Operations Research department at UC Berkeley, and a Research Assistant Professor in the Electrical and Computer Engineering department at the University of Illinois at Urbana-Champaign. His research uses tools from control theory, economics, statistics, and optimization to understand the closed-loop effects of machine learning, with applications in cyber-physical systems such as the smart grid, modern transportation networks, and autonomous vehicles.