论文标题
拍卖学习作为两人游戏
Auction learning as a two-player game
论文作者
论文摘要
设计一个兼容拍卖，使预期收入最大化是拍卖设计中的核心问题。尽管理论方法解决了问题，但Duetting等人最新的研究方向。 （2019年）包括建立神经网络体系结构以寻找最佳的拍卖。我们提出了两个概念上的偏差，从而提高了性能。首先，我们在理论拍卖设计（Rubinstein and Weinberg，2018）中使用最新结果来引入与时间无关的Lagrangian。这不仅规避了对昂贵的超参数搜索的需求（如在先前的工作中），而且提供了一个原则上的指标来比较两次拍卖的性能（在先前的工作中没有）。其次，以前工作中的优化过程使用内部最大化循环来计算最佳错误报告。我们通过引入附加的神经网络来摊销此过程。与先前的工作相比，我们通过学习竞争力或严格改善的拍卖来证明我们方法的有效性。两者的结果都进一步暗示了拍卖设计作为具有固定效用功能的两人游戏的新颖表述。
Designing an incentive compatible auction that maximizes expected revenue is a central problem in Auction Design. While theoretical approaches to the problem have hit some limits, a recent research direction initiated by Duetting et al. (2019) consists in building neural network architectures to find optimal auctions. We propose two conceptual deviations from their approach which result in enhanced performance. First, we use recent results in theoretical auction design (Rubinstein and Weinberg, 2018) to introduce a time-independent Lagrangian. This not only circumvents the need for an expensive hyper-parameter search (as in prior work), but also provides a principled metric to compare the performance of two auctions (absent from prior work). Second, the optimization procedure in previous work uses an inner maximization loop to compute optimal misreports. We amortize this process through the introduction of an additional neural network. We demonstrate the effectiveness of our approach by learning competitive or strictly improved auctions compared to prior work. Both results together further imply a novel formulation of Auction Design as a two-player game with stationary utility functions.
