Learning to Bid in Contextual First Price Auctions

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 using maximum likelihood estimation (MLE) method to achieve at most regret. Moreover, we generalize this algorithm to the setting with binary feedback and the noise distribution is unknown but belongs to a parametrized family of distributions. For the full information feedback with \emph{unknown} noise distribution, we provide an algorithm that achieves regret at most . Our approach combines an estimator for log-concave density functions and then MLE method to learn the noise distribution and linear weight simultaneously. We also provide a lower bound result such that any bidding policy in a broad class must achieve regret at least , even when the learner receives the full information feedback and is known.
View on arXiv