arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.00738math.PR
收藏

光滑Wasserstein距离的渐近性

Asymptotics of smoothed Wasserstein distances

Hong-Bin Chen, Jonathan Niles-Weed

摘要:

我们研究了高斯平滑下$\mathbb{R}^d$上Wasserstein距离的收缩。众所周知,热半群相对于正曲率流形上的Wasserstein距离是指数收缩的;然而,在平坦的欧几里得空间上-其中热半群对应于通过高斯卷积平滑测度-情况更加微妙。我们证明了精确的渐近的$2$ -Wasserstein距离的作用下的欧氏热半群,并表明,在对比的情况下,正弯曲,收缩率总是多项式,指数取决于的时刻序列的措施。我们建立了类似的结果$p$ -Wasserstein距离$p \neq 2$以及$χ^2$的分歧,相对熵,和全变差距离。总之,这些结果建立了中心作用的时刻匹配参数的高斯卷积平滑的措施的分析。

英文摘要:

We investigate contraction of the Wasserstein distances on $\mathbb{R}^d$ under Gaussian smoothing. It is well known that the heat semigroup is exponentially contractive with respect to the Wasserstein distances on manifolds of positive curvature; however, on flat Euclidean space---where the heat semigroup corresponds to smoothing the measures by Gaussian convolution---the situation is more subtle. We prove precise asymptotics for the $2$-Wasserstein distance under the action of the Euclidean heat semigroup, and show that, in contrast to the positively curved case, the contraction rate is always polynomial, with exponent depending on the moment sequences of the measures. We establish similar results for the $p$-Wasserstein distances for $p \neq 2$ as well as the $χ^2$ divergence, relative entropy, and total variation distance. Together, these results establish the central role of moment matching arguments in the analysis of measures smoothed by Gaussian convolution.

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。

↑