arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.01879math.OCcs.LGstat.ML
收藏

线性规划中熵罚的显式分析

An explicit analysis of the entropic penalty in linear programming

Massachusetts Institute of Technology(麻省理工学院)

Jonathan Weed

摘要:

通过使用熵惩罚来求解线性规划最近在优化界引起了新的兴趣,因为这种策略形成了最优输运问题的最快已知算法的基础,在现代大规模机器学习中有许多应用。这些应用程序的关键一直是如何快速解决方案的惩罚计划接近真正的最优原线性规划的分析。20多年前,Cominetti和San Martín证明了这种收敛速度是指数级的;然而,他们的证明是渐近的,并且没有给出任何关于熵程序在任何特定的惩罚参数选择下近似原始程序的精确度的指示。我们关闭这一长期存在的差距,在文献中关于熵惩罚给出了一个新的证明的指数收敛,有效的任何线性规划。我们的证明是非渐近的,产生明确的常数,并具有非常简单的优点。我们提供匹配的下界,并表明熵的方法不会导致一个近线性的时间近似计划的线性分配问题。

英文摘要:

Solving linear programs by using entropic penalization has recently attracted new interest in the optimization community, since this strategy forms the basis for the fastest-known algorithms for the optimal transport problem, with many applications in modern large-scale machine learning. Crucial to these applications has been an analysis of how quickly solutions to the penalized program approach true optima to the original linear program. More than 20 years ago, Cominetti and San Martín showed that this convergence is exponentially fast; however, their proof is asymptotic and does not give any indication of how accurately the entropic program approximates the original program for any particular choice of the penalization parameter. We close this long-standing gap in the literature regarding entropic penalization by giving a new proof of the exponential convergence, valid for any linear program. Our proof is non-asymptotic, yields explicit constants, and has the virtue of being extremely simple. We provide matching lower bounds and show that the entropic approach does not lead to a near-linear time approximation scheme for the linear assignment problem.

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。

↑