arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.08424cs.LGmath.OCstat.ME
收藏

从上下文数据到报童决策:数据驱动算法的实际性能

From Contextual Data to Newsvendor Decisions: On the Actual Performance of Data-Driven Algorithms

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

Omar Besbes, Will Ma, Omar Mouchtaki

AI总结:

本文通过精确刻画加权经验风险最小化策略在上下文报童问题中的最大遗憾,首次提供紧性能保证,并揭示数据质量与数量对决策性能的影响。

摘要:

本文通过分析上下文报童问题,研究过去数据的相关性/质量与数量如何影响性能。在该问题中,决策者在不确定需求下权衡缺货成本与过剩成本。我们考虑一个设定,其中在“邻近”上下文下观察到的过去需求来自邻近的分布,并通过上下文相关的最大期望遗憾概念分析数据驱动算法的性能。我们分析了加权经验风险最小化(WERM)策略这一广泛类别,该策略根据过去数据在上下文空间中的相似性对其加权。该类别包括经典策略,如经验风险最小化(ERM)、k近邻和基于核的策略。我们的主要方法论贡献是精确刻画任何WERM策略在任意给定上下文配置下的最大遗憾。据我们所知,这为任何上下文决策问题提供了首个紧性能保证的理解,而以往文献侧重于通过集中不等式得到上界。我们转而采用优化方法,并隔离出报童损失函数中的一种结构,该结构允许将最大分布上的无限维优化问题简化为简单的线搜索。这进而使我们能够揭示被以往通用界所掩盖的基本见解。我们刻画了实际保证性能作为上下文的函数,以及关于算法学习曲线的细粒度见解。

英文摘要:

In this work, we study how the relevance/quality and quantity of past data influence performance by analyzing a contextual Newsvendor problem, in which a decision-maker trades off between underage and overage costs under uncertain demand. We consider a setting in which past demands observed under ``close by'' contexts come from close by distributions and analyze the performance of data-driven algorithms through a notion of context-dependent worst-case expected regret. We analyze the broad class of Weighted Empirical Risk Minimization (WERM) policies which weigh past data according to their similarity in the contextual space. This class includes classical policies such as ERM, k-Nearest Neighbors and kernel-based policies. Our main methodological contribution is to characterize exactly the worst-case regret of any WERM policy on any given configuration of contexts. To the best of our knowledge, this provides the first understanding of tight performance guarantees in any contextual decision-making problem, with past literature focusing on upper bounds via concentration inequalities. We instead take an optimization approach, and isolate a structure in the Newsvendor loss function that allows to reduce the infinite-dimensional optimization problem over worst-case distributions to a simple line search. This in turn allows us to unveil fundamental insights that were obfuscated by previous general-purpose bounds. We characterize actual guaranteed performance as a function of the contexts, as well as granular insights on the learning curve of 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。

↑