Optimal No-regret Learning in Repeated First-price Auctions release_lk5tig7hyrc23amdlthmtsgyla

by Yanjun Han, Zhengyuan Zhou, Tsachy Weissman

Released as a article .

2020  

Abstract

We study online learning in repeated first-price auctions with censored feedback, where a bidder, only observing the winning bid at the end of each auction, learns to adaptively bid in order to maximize her cumulative payoff. To achieve this goal, the bidder faces a challenging dilemma: if she wins the bid–the only way to achieve positive payoffs–then she is not able to observe the highest bid of the other bidders, which we assume is iid drawn from an unknown distribution. This dilemma, despite being reminiscent of the exploration-exploitation trade-off in contextual bandits, cannot directly be addressed by the existing UCB or Thompson sampling algorithms in that literature, mainly because contrary to the standard bandits setting, when a positive reward is obtained here, nothing about the environment can be learned. In this paper, by exploiting the structural properties of first-price auctions, we develop the first learning algorithm that achieves O(√(T)log^2 T) regret bound when the bidder's private values are stochastically generated. We do so by providing an algorithm on a general class of problems, which we call monotone group contextual bandits, where the same regret bound is established under stochastically generated contexts. Further, by a novel lower bound argument, we characterize an Ω(T^2/3) lower bound for the case where the contexts are adversarially generated, thus highlighting the impact of the contexts generation mechanism on the fundamental learning limit. Despite this, we further exploit the structure of first-price auctions and develop a learning algorithm that operates sample-efficiently (and computationally efficiently) in the presence of adversarially generated private values. We establish an O(√(T)log^3 T) regret bound for this algorithm, hence providing a complete characterization of optimal learning guarantees for this problem.
In text/plain format

Archived Files and Locations

application/pdf  510.5 kB
file_hqeb7hmj6zeunpc7ijgloe4j2a
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-05-08
Version   v4
Language   en ?
arXiv  2003.09795v4
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 83ccc523-54c2-406d-9f2b-84452bf2f8ad
API URL: JSON