当前位置: X-MOL 学术Math. Meth. Stat. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Gaussian Approximation for Penalized Wasserstein Barycenters
Mathematical Methods of Statistics Pub Date : 2023-04-26 , DOI: 10.3103/s1066530723010039
Nazar Buzun

Abstract

In this work we consider regularized Wasserstein barycenters (average in Wasserstein distance) in Fourier basis. We prove that random Fourier parameters of the barycenter converge to some Gaussian random vector in distribution. The convergence rate has been derived in finite-sample case with explicit dependence on measures count (\(n\)) and the dimension of parameters (\(p\)).



中文翻译:

惩罚 Wasserstein 重心的高斯近似

摘要

在这项工作中,我们在傅立叶基础上考虑正则化的 Wasserstein 重心(Wasserstein 距离的平均值)。我们证明了重心的随机傅里叶参数收敛于分布中的某个高斯随机向量。收敛速度是在有限样本情况下导出的,明确依赖于测量计数 ( \(n\) ) 和参数维度 ( \(p\) )。

更新日期:2023-04-27
down
wechat
bug