Seminars topic: The short course offers an overview of learning in repeated first-price auctions from an online-learning perspective. It introduces three methodological tools: (1) learning from experts’ advice in an unknown and possibly adversarial environment; (2) stochastic bandits with graph feedback; and (3) Le Cam’s two-point method for proving lower bounds.

Scholars Background: Zhengyuan Zhou is an Associate Professor at New York University’s Stern School of Business (Department of Technology, Operations and Statistics). He was a Goldstine Research Fellow at IBM Research in 2019–2020. He received a BA in Mathematics and a BS in Electrical Engineering and Computer Sciences from UC Berkeley, and a PhD in Electrical Engineering from Stanford University in 2019. His research interests lie at the intersection of machine learning, stochastic optimization and game theory, with a focus on methodological frameworks for data-driven decision making.

Time and Location: July 28–31, 2025, 09:00–12:00, Room A203, School of Management

Language: Bilingual (ENG & CN)