arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.13380stat.MLcs.LG
收藏

基于最优弱质量输运的概率分布重心新概念

A novel notion of barycenter for probability distributions based on optimal weak mass transport

IRIT, Université de Toulouse, CNRS(法国国家科学研究中心、图卢兹大学信息与电信研究所);IDIA & CMM, Universidad de Chile(智利大学数据与人工智能研究所、智利大学数学建模中心);CMM, Universidad de Chile(智利大学数学建模中心)

Elsa Cazelles, Felipe Tobar, Joaquín Fontbona

摘要:

基于Gozlanet al.(2017)和Backhoff-Veraguas et al.(2020)最近提出的最优弱质量输运概念,我们引入了一个概率分布族的弱重心。我们提供了一个理论分析,并讨论了它的解释,根据凸序之间的概率测度。特别是,我们表明,而不是平均的输入分布的几何方式(如Wasserstein重心的基础上经典的最佳运输)弱重心提取共同的几何信息共享的所有输入分布,编码为一个潜在的随机变量,所有这些。我们还提供了一个迭代算法来计算一个有限的家庭的输入分布的弱重心,和随机算法,计算他们的任意人口的法律。后一种方法特别适合于流设置,即,当按顺序观察分布时。弱重心的概念和我们的方法来计算它说明合成的例子,验证2D真实世界的数据和标准的Wasserstein重心。

英文摘要:

We introduce weak barycenters of a family of probability distributions, based on the recently developed notion of optimal weak transport of mass by Gozlanet al. (2017) and Backhoff-Veraguas et al. (2020). We provide a theoretical analysis of this object and discuss its interpretation in the light of convex ordering between probability measures. In particular, we show that, rather than averaging the input distributions in a geometric way (as the Wasserstein barycenter based on classic optimal transport does) weak barycenters extract common geometric information shared by all the input distributions, encoded as a latent random variable that underlies all of them. We also provide an iterative algorithm to compute a weak barycenter for a finite family of input distributions, and a stochastic algorithm that computes them for arbitrary populations of laws. The latter approach is particularly well suited for the streaming setting, i.e., when distributions are observed sequentially. The notion of weak barycenter and our approaches to compute it are illustrated on synthetic examples, validated on 2D real-world data and compared to standard Wasserstein barycenters.

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。

↑