arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.06259cs.GTcs.DSstat.ML
收藏

最优拍卖的鲁棒学习

Robust Learning of Optimal Auctions

Wenshuo Guo, Michael I. Jordan, Manolis Zampetakis

摘要:

我们研究的问题学习收益最优的多投标人拍卖的样本时,投标人的估值样本可以是adversarially损坏或从分布是adversarially扰动。首先,我们证明紧上界的收入,我们可以得到一个腐败的分布下的人口模型,定期估值分布和分布单调风险率(MHR)。然后,我们提出了新的算法,只给出一个"近似分布“的投标人的估值,可以学习的机制,其收入几乎是最佳的同时为所有的"真正的分布”是$α$ -接近原来的分布在Kolmogorov-Smirnov距离。所提出的算法超出了有界分布的设置,已经在以前的作品中研究,并保证获得一个分数$1-O(α)$的最优收益下的真实分布时,分布MHR。此外,当分布是规则的时,它们保证产生最优收入的至少一部分$1-O(\sqrtα)$。我们证明,这些上限不能进一步提高,通过提供匹配的下限。最后,我们推导出样本复杂度上界学习MHR和常规分布的近最优拍卖。

英文摘要:

We study the problem of learning revenue-optimal multi-bidder auctions from samples when the samples of bidders' valuations can be adversarially corrupted or drawn from distributions that are adversarially perturbed. First, we prove tight upper bounds on the revenue we can obtain with a corrupted distribution under a population model, for both regular valuation distributions and distributions with monotone hazard rate (MHR). We then propose new algorithms that, given only an ``approximate distribution'' for the bidder's valuation, can learn a mechanism whose revenue is nearly optimal simultaneously for all ``true distributions'' that are $α$-close to the original distribution in Kolmogorov-Smirnov distance. The proposed algorithms operate beyond the setting of bounded distributions that have been studied in prior works, and are guaranteed to obtain a fraction $1-O(α)$ of the optimal revenue under the true distribution when the distributions are MHR. Moreover, they are guaranteed to yield at least a fraction $1-O(\sqrtα)$ of the optimal revenue when the distributions are regular. We prove that these upper bounds cannot be further improved, by providing matching lower bounds. Lastly, we derive sample complexity upper bounds for learning a near-optimal auction for both MHR and regular distributions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑