English

The Sample Complexity of Up-to-$\varepsilon$ Multi-Dimensional Revenue Maximization

Computer Science and Game Theory 2021-04-13 v4 Machine Learning

Abstract

We consider the sample complexity of revenue maximization for multiple bidders in unrestricted multi-dimensional settings. Specifically, we study the standard model of nn additive bidders whose values for mm heterogeneous items are drawn independently. For any such instance and any ε>0\varepsilon>0, we show that it is possible to learn an ε\varepsilon-Bayesian Incentive Compatible auction whose expected revenue is within ε\varepsilon of the optimal ε\varepsilon-BIC auction from only polynomially many samples. Our fully nonparametric approach is based on ideas that hold quite generally, and completely sidestep the difficulty of characterizing optimal (or near-optimal) auctions for these settings. Therefore, our results easily extend to general multi-dimensional settings, including valuations that are not necessarily even subadditive, and arbitrary allocation constraints. For the cases of a single bidder and many goods, or a single parameter (good) and many bidders, our analysis yields exact incentive compatibility (and for the latter also computational efficiency). Although the single-parameter case is already well-understood, our corollary for this case extends slightly the state-of-the-art.

Keywords

Cite

@article{arxiv.1808.02458,
  title  = {The Sample Complexity of Up-to-$\varepsilon$ Multi-Dimensional Revenue Maximization},
  author = {Yannai A. Gonczarowski and S. Matthew Weinberg},
  journal= {arXiv preprint arXiv:1808.02458},
  year   = {2021}
}
R2 v1 2026-06-23T03:27:03.560Z