arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.00618cs.DScs.LGmath.OCstat.COstat.ML
收藏

最优运输问题的直接$\tilde{O}(1/ε)$迭代并行算法

A Direct $\tilde{O}(1/ε)$ Iteration Parallel Algorithm for Optimal Transport

Stanford University(斯坦福大学)

Arun Jambulapati, Aaron Sidford, Kevin Tian

摘要:

最佳运输,或计算两个分布之间的瓦瑟斯坦或“地球移动者”距离,是一个基本的原始,出现在许多学习和统计设置。我们给出了一个算法,解决了这个问题的可加$ε$与$\tilde{O}(1/ε)$并行深度,和$\tilde{O}\left(n^2/ε\right)$工作。除非在一个长期存在的算法开放问题上取得突破,否则这对于一阶方法来说是最优的。布朗谢等Quanrud等人的'18,Quanrud '19通过减少到正线性规划和矩阵缩放获得了类似的运行时间。然而,这些基于约简的算法使用复杂的子程序,由于需要求解器进行二阶迭代(矩阵缩放)或非并行化(正LP),这些子程序可能被认为是不切实际的。最快的实用算法在时间上运行$\tilde{O}(\min(n^2 / ε^2, n^{2.5} / ε))$(Dvurechensky et. 18,Lin et. 19)。我们提供了一个并行的,一阶的,$\tilde{O}(1/ε)$迭代算法,没有更好的依赖于尺寸,并提供初步的实验证据表明,我们的算法可以享受改善的实际性能。我们通过原始-对偶超梯度方法获得此运行时间,其动机是最近对最大流的理论改进(Sherman '17)。

英文摘要:

Optimal transportation, or computing the Wasserstein or ``earth mover's'' distance between two distributions, is a fundamental primitive which arises in many learning and statistical settings. We give an algorithm which solves this problem to additive $ε$ with $\tilde{O}(1/ε)$ parallel depth, and $\tilde{O}\left(n^2/ε\right)$ work. Barring a breakthrough on a long-standing algorithmic open problem, this is optimal for first-order methods. Blanchet et. al. '18, Quanrud '19 obtained similar runtimes through reductions to positive linear programming and matrix scaling. However, these reduction-based algorithms use complicated subroutines which may be deemed impractical due to requiring solvers for second-order iterations (matrix scaling) or non-parallelizability (positive LP). The fastest practical algorithms run in time $\tilde{O}(\min(n^2 / ε^2, n^{2.5} / ε))$ (Dvurechensky et. al. '18, Lin et. al. '19). We bridge this gap by providing a parallel, first-order, $\tilde{O}(1/ε)$ iteration algorithm without worse dependence on dimension, and provide preliminary experimental evidence that our algorithm may enjoy improved practical performance. We obtain this runtime via a primal-dual extragradient method, motivated by recent theoretical improvements to maximum flow (Sherman '17).

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。

↑