arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.12364math.STmath.OCstat.TH
收藏

随机线性规划的渐近置信集

Asymptotic confidence sets for random linear programs

Shuyu Liu, Florentina Bunea, Jonathan Niles-Weed

摘要:

受离散最优输运问题的统计分析的启发,我们证明了随机约束线性规划解的分布极限。这种极限最早是由Klatt,Munk,& Zemel(2022)得到的,但是他们的极限表达式涉及到将$\mathbb{R}^m$分解成可能是指数数量的凸锥的计算上的困难。我们用辅助线性规划的形式给出了极限的一个新的表达式,它可以在多项式时间内求解。我们还利用随机凸几何的工具,给整个随机最优解集的分布限制,当最优解不是唯一的。最后,我们描述了一个简单的,数据驱动的方法,在多项式时间内构造渐近有效的置信集。

英文摘要:

Motivated by the statistical analysis of the discrete optimal transport problem, we prove distributional limits for the solutions of linear programs with random constraints. Such limits were first obtained by Klatt, Munk, & Zemel (2022), but their expressions for the limits involve a computationally intractable decomposition of $\mathbb{R}^m$ into a possibly exponential number of convex cones. We give a new expression for the limit in terms of auxiliary linear programs, which can be solved in polynomial time. We also leverage tools from random convex geometry to give distributional limits for the entire set of random optimal solutions, when the optimum is not unique. Finally, we describe a simple, data-driven method to construct asymptotically valid confidence sets in polynomial time.

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。

↑