Jolley Hall, Room 309
Robustness and Strategic Concerns in Machine Learnings
Most people interact with machine learning systems on a daily basis. Such interactions often happen in strategic environments where people have incentives to manipulate the outcome of the learning algorithms. As machine learning plays a more prominent role in our society, it is important to understand how people's incentives can affect the learning problems, and to design reliable algorithms that perform well in these strategic environments.
In this talk, I will explore the challenges that arise at the interface of machine learning and game theory: selfish agents may interact with machine learning algorithms strategically rather than truthfully, and many existing algorithms are vulnerable to adversarial attacks. I will discuss two lines of my work that address these challenges: designing fast algorithms that are provably robust for several fundamental problems in machine learning and statistics, when the input data is modified by an adversary; and finding optimal policies for collecting data from selfish agents.
Yu Cheng is a postdoctoral researcher in the Department of Computer Science at Duke University, hosted by Vincent Conitzer, Rong Ge, Kamesh Munagala, and Debmalya Panigrahi. He obtained his Ph.D. in Computer Science from the University of Southern California in 2017, advised by Shang-Hua Teng. His research interests include machine learning, game theory, and optimization.