We consider the sample complexity of revenue maximization for multiple bidders in unrestricted multi-dimensional settings. Specifically, we study the standard model of $n$ additive bidders whose values for $m$ heterogeneous items are drawn independently. For any such instance and any $\varepsilon>0$, we show that it is possible to learn an $\varepsilon$-Bayesian Incentive Compatible auction whose expected revenue is within $\varepsilon$ of the optimal $\varepsilon$-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.
翻译:我们考虑了在不受限制的多维环境下为多个投标人实现最大收入的抽样复杂性。 具体地说, 我们研究的是美元添加投标人的标准模式, 其价值为百万美元的多元项目的价值是独立抽取的。 对于任何此类案例和任何美元(varepsilon>0美元),我们表明,我们有可能学习一个美元(varepsilon$-Bayesian)的刺激性兼容性拍卖,其预期收入在美元(varepsilon$@varepsilon-BIC)范围内,其预期收入在美元(varepsilon-BIC)最佳拍卖中,仅来自多个样本。 我们的完全非对称法方法基于一些观念,这些观念非常笼统,完全回避了为这些背景确定最佳(或接近最佳)拍卖特征的困难。 因此,我们的结果很容易扩展到一般的多维维度环境, 包括不一定是次要的估值, 以及任意的分配限制。 对于单一投标人和许多货物, 或单一参数( 良好) 和许多投标人来说, 我们的分析得出了准确的激励性兼容性( 以及后者也是计算效率 ) 。 尽管单数案例已经略扩展了我们的必然结果。