Learning to Bid in Contextual First Price Auctions
Ashwinkumar Badanidiyuru, Zhe Feng, Guru Guruganesh

TL;DR
This paper develops algorithms for bidding in repeated contextual first-price auctions, achieving low regret bounds by estimating unknown parameters and noise distributions, with theoretical guarantees under different feedback settings.
Contribution
It introduces novel algorithms for bidding with unknown noise distributions and provides regret bounds, extending previous work to more realistic auction scenarios.
Findings
Achieves regret of (\u007f\u0010(\u007fig( ext{log}(d) Tig) ight) in known noise distribution case.
Extends algorithms to unknown noise distributions within a parametrized family, maintaining low regret.
Provides lower bounds indicating the fundamental difficulty of the problem.
Abstract
In this paper, we investigate the problem about how to bid in repeated contextual first price auctions. We consider a single bidder (learner) who repeatedly bids in the first price auctions: at each time , the learner observes a context and decides the bid based on historical information and . We assume a structured linear model of the maximum bid of all the others , where is unknown to the learner and is randomly sampled from a noise distribution with log-concave density function . We consider both \emph{binary feedback} (the learner can only observe whether she wins or not) and \emph{full information feedback} (the learner can observe ) at the end of each time . For binary feedback, when the noise distribution is known, we propose a bidding algorithm, by…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAuction Theory and Applications · Advanced Bandit Algorithms Research · Experimental Behavioral Economics Studies
