arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.04016math.NAcs.NAmath.PR
收藏

计算通用传输成本下的测度barycentre

Computing Barycentres of Measures for Generic Transport Costs

Université Paris Cité, CNRS, MAP5(巴黎西岱大学,法国国家科学研究中心,MAP5)

Eloi Tanguy, Julie Delon, Nathaël Gozlan

AI总结:

本文研究了通用传输成本下barycentre的固定点方法,探讨其推广至更广泛传输成本和概率测度的应用,并展示收敛性结果及数值表现。

摘要:

Wasserstein barycentres代表多个概率测度在Wasserstein距离下的平均分布。数值计算Wasserstein barycentres notoriously具有挑战性。常用方法是使用Sinkhorn迭代,引入熵正则化项使问题更易处理。另一种方法是使用固定点方法,类似于计算流形上Fréchet均值的方法。Alvarez-Esteban等人(2016)研究了此类方法在2-Wasserstein barycentres上的收敛性,特别是在二次成本函数和绝对连续测度的情况下。本文深入探讨此固定点方法的核心思想,并探讨其如何推广到更广泛的传输成本和通用概率测度,从而扩展其应用范围。我们展示了此方法的收敛性结果,并在多个barycentre问题上展示了其数值行为。

英文摘要:

Wasserstein barycentres represent average distributions between multiple probability measures for the Wasserstein distance. The numerical computation of Wasserstein barycentres is notoriously challenging. A common approach is to use Sinkhorn iterations, where an entropic regularisation term is introduced to make the problem more manageable. Another approach involves using fixed-point methods, akin to those employed for computing Fréchet means on manifolds. The convergence of such methods for 2-Wasserstein barycentres, specifically with a quadratic cost function and absolutely continuous measures, was studied by Alvarez-Esteban et al. (2016). In this paper, we delve into the main ideas behind this fixed-point method and explore how it can be generalised to accommodate more diverse transport costs and generic probability measures, thereby extending its applicability to a broader range of problems. We show convergence results for this approach and illustrate its numerical behaviour on several barycentre 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。

↑