中文
相关论文

相关论文: Quantitative Stability of Barycenters in the Wasse…

200 篇论文

We study barycenters of $N$ probability measures on $\mathbb{R}^d$ with respect to the $p$-Wasserstein metric ($1<p<\infty$). We prove that -- $p$-Wasserstein barycenters of absolutely continuous measures are unique, and again absolutely…

偏微分方程分析 · 数学 2024-10-23 Camilla Brizzi , Gero Friesecke , Tobias Ried

The Wasserstein barycenter extends the Euclidean mean to the space of probability measures by minimizing the weighted sum of squared 2-Wasserstein distances. We develop a free-support algorithm for computing Wasserstein barycenters that…

机器学习 · 统计学 2025-09-17 Kisung You

Barycenter problems encode important geometric information about a metric space. While these problems are typically studied with positive weight coefficients associated to each distance term, more general signed Wasserstein barycenter…

最优化与控制 · 数学 2026-02-06 Matt Jacobs , Bohan Zhou

In this paper, a regularization of Wasserstein barycenters for random measures supported on $\mathbb{R}^{d}$ is introduced via convex penalization. The existence and uniqueness of such barycenters is first proved for a large class of…

统计理论 · 数学 2019-03-20 Jérémie Bigot , Elsa Cazelles , Nicolas Papadakis

Let $\mathcal{P}_{2,ac}$ be the set of Borel probabilities on $\mathbb{R}^d$ with finite second moment and absolutely continuous with respect to Lebesgue measure. We consider the problem of finding the barycenter (or Fr\'echet mean) of a…

统计计算 · 统计学 2016-04-25 Pedro C. Álvarez-Esteban , E. del Barrio , J. A. Cuesta-Albertos , C. Matrán

This paper studies the statistical estimation of exact Wasserstein barycenters. Existing non-asymptotic results for empirical barycenters exhibit a severe curse of dimensionality. Motivated by the semi-dual formulation of the barycenter…

统计理论 · 数学 2026-05-06 Pengtao Li , Changbo Zhu , Xiaohui Chen

We study the problem of model aggregation within the Wasserstein space for probability measures on the real line. Given a fixed finite collection of candidate probability models, we consider the associated class of Wasserstein barycenters…

统计方法学 · 统计学 2026-05-20 Emmanouil Androulakis , Georgios I. Papayiannis , Athanasios N. Yannacopoulos

Computational implementation of optimal transport barycenters for a set of target probability measures requires a form of approximation, a widespread solution being empirical approximation of measures. We provide an $O(\sqrt{N/n})$…

最优化与控制 · 数学 2025-11-19 Léo Portales , Edouard Pauwels , Elsa Cazelles

In this paper, we focus on the analysis of the regularized Wasserstein barycenter problem. We provide uniqueness and a characterization of the barycenter for two important classes of probability measures: (i) Gaussian distributions and (ii)…

最优化与控制 · 数学 2022-08-09 S. Kum , M. H. Duong , Y. Lim , S. Yun

A common feature of methods for analyzing samples of probability density functions is that they respect the geometry inherent to the space of densities. Once a metric is specified for this space, the Fr\'echet mean is typically used to…

统计方法学 · 统计学 2018-12-20 Alexander Petersen , Hans-Georg Müller

The optimal transport barycenter (a.k.a. Wasserstein barycenter) is a fundamental notion of averaging that extends from the Euclidean space to the Wasserstein space of probability distributions. Computation of the unregularized barycenter…

机器学习 · 统计学 2025-05-27 Kaheon Kim , Rentian Yao , Changbo Zhu , Xiaohui Chen

Wasserstein barycenters have become popular due to their ability to represent the average of probability measures in a geometrically meaningful way. In this paper, we present an algorithm to approximate the Wasserstein-2 barycenters of…

机器学习 · 计算机科学 2023-01-10 Alexander Korotin , Vage Egiazarian , Lingxiao Li , Evgeny Burnaev

Computing Wasserstein barycenters of discrete measures has recently attracted considerable attention due to its wide variety of applications in data science. In general, this problem is NP-hard, calling for practical approximative…

数值分析 · 数学 2023-01-25 Johannes von Lindheim

This paper is focused on the statistical analysis of probability measures $\nu_{1},\ldots,\nu_{n}$ on $\mathbb{R}$ that can be viewed as independent realizations of an underlying stochastic process. We consider the situation of practical…

统计理论 · 数学 2017-03-30 Jérémie Bigot , Raúl Gouet , Thierry Klein , Alfredo López

In many applications in statistics and machine learning, the availability of data samples from multiple possibly heterogeneous sources has become increasingly prevalent. On the other hand, in distributionally robust optimization, we seek…

机器学习 · 统计学 2022-05-31 Tim Tsz-Kit Lau , Han Liu

We introduce and study a variant of the Wasserstein distance on the space of probability measures, specially designed to deal with measures whose support has a dendritic, or treelike structure with a particular direction of orientation. Our…

最优化与控制 · 数学 2020-11-18 Young-Heon Kim , Brendan Pass , David J. Schneider

This work presents an algorithm to sample from the Wasserstein barycenter of absolutely continuous measures. Our method is based on the gradient flow of the multimarginal formulation of the Wasserstein barycenter, with an additive…

机器学习 · 计算机科学 2021-05-06 Chiheb Daaloul , Thibaut Le Gouic , Jacques Liandrat , Magali Tournus

The Wasserstein barycenter (WB) is an important tool for summarizing sets of probability measures. It finds applications in applied probability, clustering, image processing, etc. When the measures' supports are finite, computing a…

最优化与控制 · 数学 2024-10-25 Daniel Mimouni , P Malisani , J. Zhu , W. de Oliveira

This paper is concerned by statistical inference problems from a data set whose elements may be modeled as random probability measures such as multiple histograms or point clouds. We propose to review recent contributions in statistics on…

统计理论 · 数学 2019-08-27 Jérémie Bigot

We study a general formulation of regularized Wasserstein barycenters that enjoys favorable regularity, approximation, stability and (grid-free) optimization properties. This barycenter is defined as the unique probability measure that…

最优化与控制 · 数学 2025-07-28 Lénaïc Chizat