log in  |  register  |  feedback?  |  help  |  web accessibility
PhD Defense: Learning and Robustness With Applications to Mechanism Design
Michael Curry
Friday, July 22, 2022, 11:00 am-1:00 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)
The design of economic mechanisms, especially auctions, is an increasingly important part of the modern economy. A particularly valuable property for a mechanism is strategyproofness: the mechanism must be robust to strategic manipulations so that the participants in the mechanism have no incentive to lie. Yet in the important case when the mechanism designer’s goal is to maximize their own revenue, the design of optimal strategyproof mechanisms has proved immensely difficult, with very little progress after decades of research. Recently, to escape this impasse, a number of works have parameterized auction mechanisms as deep neural networks and used gradient descent to successfully learn approximately optimal and approximately strategyproof mechanisms. We present several improvements on these techniques in order to ensure allocations satisfy desirable properties such as fairness, to ensure that violations of strategyproofness can be measured, and (with some compromises) to ensure that strategyproofness is always perfectly satisfied.

Examining Committee:
Dean's Representative:
Dr. John Dickerson    
Dr. Tom Goldstein
Dr. Daniel Vincent   
Dr. Aravind Srinivasan    
Dr. Ian Kash (Univ. of IL-Chicago)

Michael Curry is a fifth-year Ph.D. student advised by John Dickerson and Tom Goldstein and affiliated with the Center for Machine Learning. His research has focused on machine learning, adversarial robustness, and the use of ML techniques for problems in allocation and mechanism design.

This talk is organized by Tom Hurst