Learning Revenue-Maximizing Auctions With Differentiable Matching
Learning Revenue-Maximizing Auctions With Differentiable Matching
复制标题
DOI：
--
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Michael J. Curry;Uro Lyi;T. Goldstein;John P. Dickerson
中科院分区：
文献类型：
--
作者：
Michael J. Curry;Uro Lyi;T. Goldstein;John P. Dickerson
我们提出了一个新的体系结构，以大致学习兼容的激励措施，从而使收入最大化的拍卖来自采样估值。我们的体系结构使用sindhorn算法来执行可区分的两分匹配，该匹配使网络能够在以前的遗憾架构无法学习的设置中学习策略性范围的收益最大化机制。特别是，我们的体系结构能够在设置中学习机制，而无需免费处理，必须将每个投标人精确分配到一些项目中。在实验中，我们显示了我们的方法成功恢复了最佳机制未知的较大设置中的多种已知最佳机制和高收益，低温机制。
We propose a new architecture to approximately learn incentive compatible, revenue-maximizing auctions from sampled valuations. Our architecture uses the Sinkhorn algorithm to perform a differentiable bipartite matching which allows the network to learn strategyproof revenue-maximizing mechanisms in settings not learnable by the previous RegretNet architecture. In particular, our architecture is able to learn mechanisms in settings without free disposal where each bidder must be allocated exactly some number of items. In experiments, we show our approach successfully recovers multiple known optimal mechanisms and high-revenue, low-regret mechanisms in larger settings where the optimal mechanism is unknown.