Efficient Algorithms for Stochastic Repeated Second-price Auctions

by   Juliette Achddou, et al.

Developing efficient sequential bidding strategies for repeated auctions is an important practical challenge in various marketing tasks. In this setting, the bidding agent obtains information, on both the value of the item at sale and the behavior of the other bidders, only when she wins the auction. Standard bandit theory does not apply to this problem due to the presence of action-dependent censoring. In this work, we consider second-price auctions and propose novel, efficient UCB-like algorithms for this task. These algorithms are analyzed in the stochastic setting, assuming regularity of the distribution of the opponents' bids. We provide regret upper bounds that quantify the improvement over the baseline algorithm proposed in the literature. The improvement is particularly significant in cases when the value of the auctioned item is low, yielding a spectacular reduction in the order of the worst-case regret. We further provide the first parametric lower bound for this problem that applies to generic UCB-like strategies. As an alternative, we propose more explainable strategies which are reminiscent of the Explore Then Commit bandit algorithm. We provide a critical analysis of this class of strategies, showing both important advantages and limitations. In particular, we provide a minimax lower bound and propose a nearly minimax-optimal instance of this class.


page 1

page 2

page 3

page 4


Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem

We study the K-armed dueling bandit problem, a variation of the standard...

Multinomial Logit Bandit with Low Switching Cost

We study multinomial logit bandit with limited adaptivity, where the alg...

Instance-Dependent Regret Analysis of Kernelized Bandits

We study the kernelized bandit problem, that involves designing an adapt...

Fast Rate Learning in Stochastic First Price Bidding

First-price auctions have largely replaced traditional bidding approache...

Repeated Bilateral Trade Against a Smoothed Adversary

We study repeated bilateral trade where an adaptive σ-smooth adversary g...

The Role of Transparency in Repeated First-Price Auctions with Unknown Valuations

We study the problem of regret minimization for a single bidder in a seq...

Learning in Repeated Multi-Unit Pay-As-Bid Auctions

Motivated by Carbon Emissions Trading Schemes, Treasury Auctions, and Pr...

Please sign up or login with your details

Forgot password? Click here to reset