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 2102.07956math.OCcs.LG
收藏

最优输运的有效离散化

Efficient Discretizations of Optimal Transport

Rutgers University(罗格斯大学)

Junqi Wang, Pei Wang, Patrick Shafto

摘要:

当边界空间是连续的时,获得最优运输(OT)问题的解通常是棘手的。最近的研究集中在近似连续的解决方案与离散化方法的基础上i.i.d.抽样,并已证明收敛的样本量增加。然而,获得具有大样本量的OT解决方案需要密集的计算工作,这在实践中可能是禁止的。在本文中,我们提出了一种算法,计算离散化与给定数量的点的边缘分布,通过最小化(熵正则化)Wasserstein距离,并导致计划,是可比的,获得了更大数量的i.i.d.样品此外,这种离散化,这是并行大规模应用程序的本地版本提出。我们证明了我们的近似范围,并展示了广泛的问题上的性能。

英文摘要:

Obtaining solutions to Optimal Transportation (OT) problems is typically intractable when the marginal spaces are continuous. Recent research has focused on approximating continuous solutions with discretization methods based on i.i.d. sampling, and has proven convergence as the sample size increases. However, obtaining OT solutions with large sample sizes requires intensive computation effort, that can be prohibitive in practice. In this paper, we propose an algorithm for calculating discretizations with a given number of points for marginal distributions, by minimizing the (entropy-regularized) Wasserstein distance, and result in plans that are comparable to those obtained with much larger numbers of i.i.d. samples. Moreover, a local version of such discretizations which is parallelizable for large scale applications is proposed. We prove bounds for our approximation and demonstrate performance on a wide range of problems.

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。

↑