Risk Guarantees for End-to-End Prediction and Optimization Processes
Risk Guarantees for End-to-End Prediction and Optimization Processes
复制标题
端到端预测和优化流程的风险保证
DOI：
10.1287/mnsc.2022.4321
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
F. Kılınç
中科院分区：
文献类型：
--
作者：
Nam Ho;F. Kılınç
预测方法经常被用来估计优化模型的参数。虽然端到端框架的目标是在后续优化模型上实现良好的性能，但对预测方法影响优化性能的方式缺乏正式的理解。本文确定的预测方法，可以保证良好的优化性能的条件。我们提供了两种类型的结果：渐近保证下一个著名的Fisher一致性准则和非渐近性能界下一个更严格的标准。我们使用这些结果来分析几种现有预测方法的优化性能，并表明在某些情况下，针对优化问题定制的方法可能无法保证良好的性能。相反，优化不可知的方法有时可以令人惊讶地有很好的保证。在投资组合优化，分数背包和多类分类问题的计算研究中，我们比较了几种预测方法的优化性能。我们证明，缺乏Fisher一致性的预测方法确实可以对性能产生不利影响。这篇论文被Chung Piao Teo采纳，优化。
Prediction methods are often employed to estimate parameters of optimization models. Although the goal in an end-to-end framework is to achieve good performance on the subsequent optimization model, a formal understanding of the ways in which prediction methods can affect optimization performance is notably lacking. This paper identifies conditions on prediction methods that can guarantee good optimization performance. We provide two types of results: asymptotic guarantees under a well-known Fisher consistency criterion and nonasymptotic performance bounds under a more stringent criterion. We use these results to analyze optimization performance for several existing prediction methods and show that in certain settings, methods tailored to the optimization problem can fail to guarantee good performance. Conversely, optimization-agnostic methods can sometimes, surprisingly, have good guarantees. In a computational study on portfolio optimization, fractional knapsack, and multiclass classification problems, we compare the optimization performance of several prediction methods. We demonstrate that lack of Fisher consistency of the prediction method can indeed have a detrimental effect on performance. This paper was accepted by Chung Piaw Teo, optimization.