Events Calendar

CS Colloq: Dr. Alex Slivkins

Title:
"Learning in a Pay-per-Click Auction:
Characterizing Truthful Multi-Armed Bandit Mechanisms"Speaker: Dr. Alex Slivkins (Microsoft Research SVC)Host: Prof. David KempeABSTRACT: 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.Joint work with Moshe Babaioff (Microsoft Research SVC) and Yogi Sharma (Cornell), published in ACM EC, 2009.BIO:
Dr. Alex Slivkins is a researcher at Microsoft Research, Silicon Valley Center. He received his PhD from Cornell University's CS department, advised by Jon Kleinberg, and then was a Postdoc at Brown University, working with Eli Upfal.
His research area is the design and analysis of algorithms. Specific topics of interest include large networks, metric embeddings, online learning, and mechanism design.

Location: Charles Lee Powell Hall (PHE) - 333

Audiences: Everyone Is Invited

Contact: CS Front Desk