中文
相关论文

相关论文: Rigidity and Quantitative Stability of the Sliced …

200 篇论文

Making sense of Wasserstein distances between discrete measures in high-dimensional settings remains a challenge. Recent work has advocated a two-step approach to improve robustness and facilitate the computation of optimal transport, using…

机器学习 · 计算机科学 2019-09-04 François-Pierre Paty , Marco Cuturi

We study the perturbation of a measure $\mu \in \mathscr{P}(\mathbb{R})$ consisting in superposing two copies of $\mu$, each slightly shifted by a small distance $\pm h$. The difference between $\mu$ and its perturbation is measured with a…

最优化与控制 · 数学 2026-03-03 Averil Aussedat

The sliced Wasserstein distance as well as its variants have been widely considered in comparing probability measures defined on $\mathbb R^d$. Here we derive the notion of sliced Wasserstein distance for measures on an infinite dimensional…

度量几何 · 数学 2025-12-10 Ruiyu Han

Given a determinate (multivariate) probability measure $\mu$, we characterize Gaussian mixtures $\nu\_\phi$ which minimize the Wasserstein distance $W\_2(\mu,\nu\_\phi)$ to $\mu$ when the mixing probability measure $\phi$ on the parameters…

最优化与控制 · 数学 2024-05-01 Jean-Bernard Lasserre

Gaussian mixture models (GMM) are powerful parametric tools with many applications in machine learning and computer vision. Expectation maximization (EM) is the most popular algorithm for estimating the GMM parameters. However, EM…

计算机视觉与模式识别 · 计算机科学 2017-11-17 Soheil Kolouri , Gustavo K. Rohde , Heiko Hoffmann

Sliced Wasserstein distances are widely used in practice as a computationally efficient alternative to Wasserstein distances in high dimensions. In this paper, motivated by theoretical foundations of this alternative, we prove quantitative…

统计理论 · 数学 2025-10-21 Guillaume Carlier , Alessio Figalli , Quentin Mérigot , Yi Wang

The Wasserstein distance and its variations, e.g., the sliced-Wasserstein (SW) distance, have recently drawn attention from the machine learning community. The SW distance, specifically, was shown to have similar properties to the…

机器学习 · 计算机科学 2019-02-04 Soheil Kolouri , Kimia Nadjahi , Umut Simsekli , Roland Badeau , Gustavo K. Rohde

The sliced Wasserstein (SW) distance has been widely recognized as a statistically effective and computationally efficient metric between two probability measures. A key component of the SW distance is the slicing distribution. There are…

机器学习 · 统计学 2024-01-02 Khai Nguyen , Nhat Ho

This work investigates several aspects related to quantitative stability in optimal transport, as well as uniqueness of the dual transport problem. Our main contributions are as follows. Chapter 1: Observations regarding the quantitative…

泛函分析 · 数学 2025-10-22 William Ford

We study the stability of entropically regularized optimal transport with respect to the marginals. Lipschitz continuity of the value and H\"older continuity of the optimal coupling in $p$-Wasserstein distance are obtained under general…

最优化与控制 · 数学 2022-07-06 Stephan Eckstein , Marcel Nutz

Gromov--Wasserstein (GW) distances compare graphs, shapes, and point clouds through internal distances, without requiring a common coordinate system. This invariance is powerful, but discrete GW is a nonconvex quadratic optimal transport…

机器学习 · 计算机科学 2026-05-15 Ao Xu , Tieru Wu

Optimal transport and the Wasserstein distance $\mathcal{W}_p$ have recently seen a number of applications in the fields of statistics, machine learning, data science, and the physical sciences. These applications are however severely…

统计理论 · 数学 2024-05-24 Ruiyu Han , Cynthia Rush , Johannes Wiesel

Sliced Wasserstein (SW) distance has been widely used in different application scenarios since it can be scaled to a large number of supports without suffering from the curse of dimensionality. The value of sliced Wasserstein distance is…

机器学习 · 统计学 2023-02-07 Khai Nguyen , Tongzheng Ren , Huy Nguyen , Litu Rout , Tan Nguyen , Nhat Ho

Explicit calculations in dimension one show for Schur stable autoregressive processes with standard Gaussian noise that the ergodic convergence in the Wasserstein-$2$ distance is essentially given by the sum of the mean, which decays…

概率论 · 数学 2026-01-09 Gerardo Barrera , Paulo Henrique da Costa , Michael A. Högele

We investigate the stability of the Wasserstein distance, a metric structure on the space of probability measures arising from the theory of optimal transport, under metric ultralimits. We first show that if $(X_{i},d_{i})_{i\in\mathbb{N}}$…

度量几何 · 数学 2023-03-09 Andrew Warren

We develop the theory of a metric, which we call the $\nu$-based Wasserstein metric and denote by $W_\nu$, on the set of probability measures $\mathcal P(X)$ on a domain $X \subseteq \mathbb{R}^m$. This metric is based on a slight…

最优化与控制 · 数学 2022-09-16 Luca Nenna , Brendan Pass

Let $(M^n,g,f)$ be a Ricci shrinker such that $\textrm{Ric}_f=\frac{1}{2}g$ and the measure induced by the weighted volume element $(4\pi)^{-\frac{n}{2}}e^{-f}dv_{g}$ is a probability measure. Given a point $p\in M$, we consider two…

微分几何 · 数学 2023-09-29 Franciele Conrado , Detang Zhou

Squared Wasserstein distance is a frequently used tool to measure discrepancy between probability distributions. This distance is typically computed between empirical measures of size $n$ from two underlying random samples. Unfortunately,…

机器学习 · 统计学 2026-05-20 Peter Matthew Jacobs , Jeff M. Phillips

The object of this paper is to study estimates of $\epsilon^{-q}W_p(\mu+\epsilon\nu, \mu)$ for small $\epsilon>0$. Here $W_p$ is the Wasserstein metric on positive measures, $p>1$, $\mu$ is a probability measure and $\nu$ a signed, neutral…

概率论 · 数学 2016-04-07 Gershon Wolansky

Variational Inference approximates an unnormalized distribution via the minimization of Kullback-Leibler (KL) divergence. Although this divergence is efficient for computation and has been widely used in applications, it suffers from some…

机器学习 · 统计学 2022-07-28 Mingxuan Yi , Song Liu