不确定条件下数据驱动Optimization的保守性对抗:一种求解路径方法
Combating Conservativeness in Data-Driven Optimization under Uncertainty: A Solution Path Approach
摘要:
在数据驱动的优化中,解决方案的可行性通常通过不确定约束的“安全”重新制定来确保,使得所获得的数据驱动的解决方案对于具有高统计置信度的预言制定是可行的。这种方法通常涉及对整个可行集的隐式估计,其可以随着问题维度迅速扩展,从而导致过度保守的解决方案。在本文中,我们研究了一种基于验证的策略,以避免集估计,利用内在的低维所有可能的解决方案输出从一个给定的重新制定。我们证明了我们获得的解决方案如何满足统计可行性保证与光维依赖,以及它们是如何渐近最优的,从而被认为是最保守的考虑重新类。我们将此策略应用于几个数据驱动的优化范例,包括(分布式)鲁棒优化,样本平均近似和场景优化。数值实验表明,我们的策略相比,建立基准令人鼓舞的表现。
英文摘要:
In data-driven optimization, solution feasibility is often ensured through a "safe" reformulation of the uncertain constraints, such that an obtained data-driven solution is guaranteed to be feasible for the oracle formulation with high statistical confidence. Such approaches generally involve an implicit estimation of the whole feasible set that can scale rapidly with the problem dimension, in turn leading to over-conservative solutions. In this paper, we investigate a validation-based strategy to avoid set estimation by exploiting the intrinsic low dimensionality among all possible solutions output from a given reformulation. We demonstrate how our obtained solutions satisfy statistical feasibility guarantees with light dimension dependence, and how they are asymptotically optimal and thus regarded as the least conservative with respect to the considered reformulation classes. We apply this strategy to several data-driven optimization paradigms including (distributionally) robust optimization, sample average approximation and scenario optimization. Numerical experiments show encouraging performances of our strategy compared to established benchmarks.
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。