关于学习收益最大化的彩票菜单和两部收费制的新保证
New Guarantees for Learning Revenue Maximizing Menus of Lotteries and Two-Part Tariffs
AI总结:
本文研究彩票菜单与两部收费制两类机制的可学习性,提出首个在线学习算法并给出强遗憾界,同时改进分布设置下的运行时间,并证明现有数据驱动设计技术不足。
摘要:
我们推进了学习理论与计算经济学交叉领域近期蓬勃发展的研究方向,研究了经济学中两类重要机制的可学习性,即彩票菜单和两部收费制。前者是一类为销售多物品而设计的随机机制,已知其收益可超越确定性机制;后者则为销售单一物品的多个单位(副本)而设计,在汽车或共享单车服务等现实场景中具有应用。我们关注在两种设置下从买家估值数据中学习此类高收益机制:分布设置,即我们事先可以获取买家的估值样本;以及更具挑战性且研究较少的在线设置,即买家逐个到达且其估值不作任何分布假设。我们针对这两类机制提供了一系列结果。我们首次为彩票菜单和两部收费制提供了具有强遗憾界保证的在线学习算法。由于参数空间是无限的且收益函数具有不连续性,已知技术不能直接适用。然而,我们能够将其归约为在有限数量的专家(在我们的情形中为有限数量的参数)上进行在线学习。此外,在有限买家类型的情形下,我们展示了归约为在线线性优化,这使我们能够通过向买家呈现对应于重心跨越器的菜单来获得无遗憾保证。另外,我们提供了在分布设置下较先前工作运行时间更快的算法。最后,我们证明了近期数据驱动算法设计文献中的技术不足以解决我们所研究的问题。
英文摘要:
We advance a recently flourishing line of work at the intersection of learning theory and computational economics by studying the learnability of two classes of mechanisms prominent in economics, namely menus of lotteries and two-part tariffs. The former is a family of randomized mechanisms designed for selling multiple items, known to achieve revenue beyond deterministic mechanisms, while the latter is designed for selling multiple units (copies) of a single item with applications in real-world scenarios such as car or bike-sharing services. We focus on learning high-revenue mechanisms of this form from buyer valuation data in both distributional settings, where we have access to buyers' valuation samples up-front, and the more challenging and less-studied online settings, where buyers arrive one-at-a-time and no distributional assumption is made about their values. We provide a suite of results with regard to these two families of mechanisms. We provide the first online learning algorithms for menus of lotteries and two-part tariffs with strong regret-bound guarantees. Since the space of parameters is infinite and the revenue functions have discontinuities, the known techniques do not readily apply. However, we are able to provide a reduction to online learning over a finite number of experts, in our case, a finite number of parameters. Furthermore, in the limited buyers type case, we show a reduction to online linear optimization, which allows us to obtain no-regret guarantees by presenting buyers with menus that correspond to a barycentric spanner. In addition, we provide algorithms with improved running times over prior work for the distributional settings. Finally, we demonstrate how techniques from the recent literature in data-driven algorithm design are insufficient for our studied problems.
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。