Eastern Great Lakes Theory Workshop Talk

Characterizing Truthful Multi-Armed Bandit Mechanisms

Yogeshwer Sharma, Cornell University

Saturday, October 3, 5:15-5:30pm

ABSTRACT

We consider a multi-round auction setting motivated by pay-per-click auctions for Internet advertising. In each round the auctioneer selects an advertiser and shows her ad, which is then either clicked or not. An advertiser derives value from clicks; the value of a click is her private information. Initially, neither the auctioneer nor the advertisers have any information about the likelihood of clicks on the advertisements. The auctioneer's goal is to design a (dominant strategies) truthful mechanism that (approximately) maximizes the social welfare.

If the advertisers bid their true private values, our problem is equivalent to the "multi-armed bandit problem", and thus can be viewed as a strategic version of the latter. In particular, for both problems the quality of an algorithm can be characterized by "regret", the difference in social welfare between the algorithm and the benchmark which always selects the same "best" advertisement. We investigate how the design of multi-armed bandit algorithms is affected by the restriction that the resulting mechanism must be truthful. We find that truthful mechanisms have certain strong structural properties -- essentially, they must separate exploration from exploitation -- and they incur much higher regret than the optimal multi-armed bandit algorithms. Moreover, we provide a truthful mechanism which (essentially) matches our lower bound on regret.

This is joint work with Moshe Babaioff and Alex Slivkins.

Slides

Speaker Bio

Yogeshwer Sharma (Yogi) is a graduate student in the Computer Science department at Cornell University, where he is advised by David Williamson and Robert Kleinberg. His research focuses on theoretical aspects of computer science, especially, approximation algorithms, game theory and computational learning theory. Before coming to Cornell, he graduated from IIT Kanpur in India. He plans to graduate from Cornell in May 2010, and he likes teaching.

< Schedule < EaGL-II homepage