中文
相关论文

相关论文: Asymptotics of smoothed Wasserstein distances

200 篇论文

In this article, exponential contraction in Wasserstein distance for heat semigroups of diffusion processes on Riemannian manifolds is established under curvature conditions where Ricci curvature is not necessarily required to be…

微分几何 · 数学 2020-01-20 Li-Juan Cheng , Anton Thalmaier , Shao-Qin Zhang

Consider an empirical measure $\mathbb{P}_n$ induced by $n$ iid samples from a $d$-dimensional $K$-subgaussian distribution $\mathbb{P}$ and let $\gamma = N(0,\sigma^2 I_d)$ be the isotropic Gaussian measure. We study the speed of…

概率论 · 数学 2025-02-11 Adam Block , Zeyu Jia , Yury Polyanskiy , Alexander Rakhlin

We prove a refined contraction inequality for diffusion semigroups with respect to the Wasserstein distance on a compact Riemannian manifold taking account of the dimension. The result generalizes in a Riemannian context, the dimensional…

概率论 · 数学 2014-12-16 Ivan Gentil

We study the behavior of the Wasserstein-$2$ distance between discrete measures $\mu$ and $\nu$ in $\mathbb{R}^d$ when both measures are smoothed by small amounts of Gaussian noise. This procedure, known as Gaussian-smoothed optimal…

统计理论 · 数学 2022-06-15 Yunzi Ding , Jonathan Niles-Weed

The asymptotic behaviour of empirical measures has been studied extensively. In this paper, we consider empirical measures of given subordinated processes on complete (not necessarily compact) and connected Riemannian manifolds with…

概率论 · 数学 2022-08-17 Huaiqian Li , Bingyao Wu

Discrepancy measures between probability distributions, often termed statistical distances, are ubiquitous in probability theory, statistics and machine learning. To combat the curse of dimensionality when estimating these distances from…

统计理论 · 数学 2021-12-21 Sloan Nietert , Ziv Goldfeld , Kengo Kato

The curvature-dimension condition is a generalization of the Bochner inequality to weighted Riemannian manifolds and general metric measure spaces. It is now known to be equivalent to evolution variational inequalities for the heat…

概率论 · 数学 2015-10-28 François Bolley , Ivan Gentil , Arnaud Guillin , Kazumasa Kuwada

The Wasserstein distance between two probability measures on a metric space is a measure of closeness with applications in statistics, probability, and machine learning. In this work, we consider the fundamental question of how quickly the…

概率论 · 数学 2017-07-04 Jonathan Weed , Francis Bach

Gaussian smoothed sliced Wasserstein distance has been recently introduced for comparing probability distributions, while preserving privacy on the data. It has been shown that it provides performances similar to its non-smoothed…

机器学习 · 计算机科学 2024-04-26 Mokhtar Z. Alaya , Alain Rakotomamonjy , Maxime Berar , Gilles Gasso

We consider elliptic diffusion processes on $\mathbb R^d$. Assuming that the drift contracts distances outside a compact set, we prove that, at a sufficiently high temperature, the Markov semi-group associated to the process is a…

概率论 · 数学 2023-07-20 Pierre Monmarché

Estimating a $d$-dimensional distribution $\mu$ by the empirical measure $\hat{\mu}_n$ of its samples is an important task in probability theory, statistics and machine learning. It is well known that $\mathbb{E}[\mathcal{W}_p(\hat{\mu}_n,…

概率论 · 数学 2026-03-24 Martin Larsson , Jonghwa Park , Johannes Wiesel

We establish an equivalence between the rigidity of Wasserstein contraction along heat flows and the rigidity of Bakry--\'Emery gradient estimates for Lipschitz functions. Applying results of Ambrosio--Bru\'e--Semola and Han, we show that…

度量几何 · 数学 2025-07-28 Zhenhao Li

Estimating the rate of convergence of the empirical measure of an i.i.d. sample to the reference measure is a classical problem in probability theory. Extending recent results of Ambrosio, Stra and Trevisan on 2-dimensional manifolds, in…

概率论 · 数学 2024-02-20 Bence Borda

We prove a sharp general inequality estimating the distance of two probability measures on a compact Lie group in the Wasserstein metric in terms of their Fourier transforms. We use a generalized form of the Wasserstein metric, related by…

经典分析与常微分方程 · 数学 2021-03-12 Bence Borda

The object of study in this paper is the expected $2$-Wasserstein distance between the empirical measures of several point processes and their respective limit. For this, the main tool developed is a smoothing procedure in Euclidean spaces…

概率论 · 数学 2026-03-20 P. García Arias

The aim of this paper is to investigate the contraction properties of $p$-Wasserstein distances with respect to convolution in Euclidean spaces both qualitatively and quantitatively. We connect this question to the question of uniform…

偏微分方程分析 · 数学 2025-12-05 Max Fathi , Michael Goldman , Daniel Tsodyks

Gaussian smoothed sliced Wasserstein distance has been recently introduced for comparing probability distributions, while preserving privacy on the data. It has been shown, in applications such as domain adaptation, to provide performances…

机器学习 · 计算机科学 2021-10-22 Alain Rakotomamonjy , Mokhtar Z. Alaya , Maxime Berar , Gilles Gasso

The space of Gaussian measures on a Euclidean space is geodesically convex in the $L^2$-Wasserstein space. This space is a finite dimensional manifold since Gaussian measures are parameterized by means and covariance matrices. By…

微分几何 · 数学 2009-02-11 Asuka Takatsu

It is now well known that curvature conditions \`a la Bakry-Emery are equivalent to contraction properties of the heat semigroup with respect to the classical quadratic Wasserstein distance. However, this curvature condition may include a…

概率论 · 数学 2017-05-17 François Bolley , Ivan Gentil , Arnaud Guillin

This paper studies convergence of empirical measures smoothed by a Gaussian kernel. Specifically, consider approximating $P\ast\mathcal{N}_\sigma$, for $\mathcal{N}_\sigma\triangleq\mathcal{N}(0,\sigma^2 \mathrm{I}_d)$, by…

统计理论 · 数学 2020-05-04 Ziv Goldfeld , Kristjan Greenewald , Yury Polyanskiy , Jonathan Weed
‹ 上一页 1 2 3 10 下一页 ›