Machine Learning Lunch Meeting

Everyone is invited to the weekly Machine Learning Lunch Meetings held Fridays 12:30-1:30pm. Faculty members from Computer Sciences, Statistics, ECE, and other departments will discuss their latest groundbreaking research in machine learning. This is an opportunity to network with faculty and fellow researchers, and to learn about the cutting-edge research being conducted at our university. Please see website for more information.

Speaker: Kirthi Kandasamy (CS) and Joon Suk Huh (CS)

Abstract: In this talk, we explore a multi-round mechanism design problem involving repeated interactions with agents over a sequence of rounds. Our goal is to develop an incentive-compatible (IC) sequential mechanism that maximizes social welfare without prior knowledge of agents' type distributions. When agents are non-myopic—that is, they participate across multiple rounds and aim to maximize cumulative utility—designing such mechanisms becomes challenging, as non-myopic agents may act strategically over time. We introduce our recent work on a surprisingly simple characterization of sequential mechanism design under adversarially chosen agent types and objectives.