arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2206.09642cs.LGmath.OCstat.ML
收藏

超越独立同分布:异质环境中的数据驱动决策

Beyond IID: data-driven decision-making in heterogeneous environments

Columbia University(哥伦比亚大学);NYU Stern School of Business(纽约大学斯特恩商学院)

Omar Besbes, Will Ma, Omar Mouchtaki

AI总结:

本文研究历史数据分布与未来分布存在异质性时的数据驱动决策问题,提出基于异质性球框架和近似参数概念的分析方法,刻画SAA策略的性能边界,并针对其失效场景设计速率最优的替代策略。

摘要:

当过去的观测不能完美预示未来时——例如由于存在无法“校正”的未观测混杂因素——人们应如何利用历史数据?受这一问题驱动,我们研究了一个数据驱动的决策框架,其中历史样本由未知且不同的分布生成,这些分布被假设位于一个异质性球内,该球的半径已知,并以(同样未知的)未来(样本外)分布为中心,决策的性能将在该未来分布上进行评估。本文旨在分析中心数据驱动策略以及近似最优策略在这些异质环境中的性能,并理解性能的关键驱动因素。我们建立了第一个结果,该结果允许对一大类策略的渐近最坏情况遗憾进行上界估计。利用这一结果,对于任意积分概率度量,我们提供了对样本平均近似(SAA)所实现性能的一般性分析,该分析以异质性球的半径为函数。这一分析围绕近似参数展开,近似参数是我们引入的一个复杂性概念,用于刻画异质性与问题结构之间的相互作用如何影响SAA的性能。进而,我们通过几个被广泛研究的问题——例如报童问题、定价问题——说明了这一方法如何应用,并发现SAA的性能因问题类别与异质性的组合不同而差异显著。SAA在某些实例上的失败促使我们设计替代策略以实现速率最优性。我们推导出依赖于问题的策略,为上述说明性问题提供了强有力的保证,并为通用速率最优算法的设计与分析提供了一种原则性方法的初步结果。

英文摘要:

How should one leverage historical data when past observations are not perfectly indicative of the future, e.g., due to the presence of unobserved confounders which one cannot "correct" for? Motivated by this question, we study a data-driven decision-making framework in which historical samples are generated from unknown and different distributions assumed to lie in a heterogeneity ball with known radius and centered around the (also) unknown future (out-of-sample) distribution on which the performance of a decision will be evaluated. This work aims at analyzing the performance of central data-driven policies but also near-optimal ones in these heterogeneous environments and understanding key drivers of performance. We establish a first result which allows to upper bound the asymptotic worst-case regret of a broad class of policies. Leveraging this result, for any integral probability metric, we provide a general analysis of the performance achieved by Sample Average Approximation (SAA) as a function of the radius of the heterogeneity ball. This analysis is centered around the approximation parameter, a notion of complexity we introduce to capture how the interplay between the heterogeneity and the problem structure impacts the performance of SAA. In turn, we illustrate through several widely-studied problems -- e.g., newsvendor, pricing -- how this methodology can be applied and find that the performance of SAA varies considerably depending on the combinations of problem classes and heterogeneity. The failure of SAA for certain instances motivates the design of alternative policies to achieve rate-optimality. We derive problem-dependent policies achieving strong guarantees for the illustrative problems described above and provide initial results towards a principled approach for the design and analysis of general rate-optimal algorithms.

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。

↑