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 2207.09403math.OC
收藏

数据驱动分布式鲁棒Optimization的Wasserstein通用框架:可处理性及应用

A General Wasserstein Framework for Data-driven Distributionally Robust Optimization: Tractability and Applications

Jonathan Yu-Meng Li, Tiantian Mao

摘要:

数据驱动的分布式鲁棒优化是一种新的研究范式,其目标是寻找一种由样本数据驱动但不受采样误差影响的解决方案。一种越来越流行的方法,称为Wasserstein分布鲁棒优化(DRO),通过应用Wasserstein度量来构建一个以经验分布为中心的球,并找到一个解决方案,该解决方案可以很好地对抗来自球的最具对抗性的分布。在本文中,我们提出了一个一般的框架,研究不同的选择的Wasserstein度量,并指出现有的选择的局限性。特别是,虽然从数据驱动的角度来看,选择更高阶的Wasserstein度量是可取的,但鉴于其不太保守的性质,这样的选择从鲁棒性的角度来看代价很高-它不再适用于许多实际关注的重尾分布。我们表明,这种看似不可避免的权衡可以解决我们的框架,在那里引入了一类新的Wasserstein指标,称为连贯的Wasserstein指标。像Wasserstein DRO一样,使用一致Wasserstein度量的分布鲁棒优化,称为广义Wasserstein分布鲁棒优化(GW-DRO),具有所有期望的性能保证:有限样本保证,渐近一致性和计算易处理性。GW-DRO中的最坏情况期望问题通常是一个非凸的最优化问题,但我们提供了新的分析来证明它的易处理性,而不依赖于常见的对偶方案。我们的框架,如本文所示,提供了一个富有成效的机会,设计新颖的Wasserstein DRO模型,可应用于各种情况下,如运营管理,金融和机器学习。

英文摘要:

Data-driven distributionally robust optimization is a recently emerging paradigm aimed at finding a solution that is driven by sample data but is protected against sampling errors. An increasingly popular approach, known as Wasserstein distributionally robust optimization (DRO), achieves this by applying the Wasserstein metric to construct a ball centred at the empirical distribution and finding a solution that performs well against the most adversarial distribution from the ball. In this paper, we present a general framework for studying different choices of a Wasserstein metric and point out the limitation of the existing choices. In particular, while choosing a Wasserstein metric of a higher order is desirable from a data-driven perspective, given its less conservative nature, such a choice comes with a high price from a robustness perspective - it is no longer applicable to many heavy-tailed distributions of practical concern. We show that this seemingly inevitable trade-off can be resolved by our framework, where a new class of Wasserstein metrics, called coherent Wasserstein metrics, is introduced. Like Wasserstein DRO, distributionally robust optimization using the coherent Wasserstein metrics, termed generalized Wasserstein distributionally robust optimization (GW-DRO), has all the desirable performance guarantees: finite-sample guarantee, asymptotic consistency, and computational tractability. The worst-case expectation problem in GW-DRO is in general a nonconvex optimization problem, yet we provide new analysis to prove its tractability without relying on the common duality scheme. Our framework, as shown in this paper, offers a fruitful opportunity to design novel Wasserstein DRO models that can be applied in various contexts such as operations management, finance, and machine learning.

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。

↑