中文
相关论文

相关论文: Estimation and inference for the Wasserstein dista…

200 篇论文

The prior distribution is a crucial building block in Bayesian analysis, and its choice will impact the subsequent inference. It is therefore important to have a convenient way to quantify this impact, as such a measure of prior impact will…

统计方法学 · 统计学 2020-10-26 Fatemeh Ghaderinezhad , Christophe Ley , Ben Serrien

We obtain an estimate for the expected subspace robust Wasserstein distance between any probability measure on the unit ball of a separable Hilbert space, and its empirical distribution from $n$ i.i.d. samples.

概率论 · 数学 2025-12-05 Dakshesh Vasan

We introduce a principled way of computing the Wasserstein distance between two distributions in a federated manner. Namely, we show how to estimate the Wasserstein distance between two samples stored and kept on different devices/clients…

机器学习 · 计算机科学 2023-10-04 Alain Rakotomamonjy , Kimia Nadjahi , Liva Ralaivola

Mixtures of high dimensional Gaussian distributions have been studied extensively in statistics and learning theory. While the total variation distance appears naturally in the sample complexity of distribution learning, it is analytically…

概率论 · 数学 2022-03-11 Sami Davies , Arya Mazumdar , Soumyabrata Pal , Cyrus Rashtchian

This paper considers the fusion of multiple estimates of a spatially extended object, where the object extent is modeled as an ellipse parameterized by the orientation and semiaxes lengths. For this purpose, we propose a novel systematic…

信号处理 · 电气工程与系统科学 2019-10-09 Kolja Thormann , Marcus Baum

We present the first minimax risk bounds for estimators of the spectral measure in multivariate linear factor models, where observations are linear combinations of regularly varying latent factors. Non-asymptotic convergence rates are…

统计理论 · 数学 2024-11-12 Xuhui Zhang , Jose Blanchet , Youssef Marzouk , Viet Anh Nguyen , Sven Wang

We provide an implementation to compute the flat metric in any dimension. The flat metric, also called dual bounded Lipschitz distance, generalizes the well-known Wasserstein distance $W_1$ to the case that the distributions are of unequal…

机器学习 · 计算机科学 2025-06-17 Henri Schmidt , Christian Düll

The Wasserstein distance, rooted in optimal transport (OT) theory, is a popular discrepancy measure between probability distributions with various applications to statistics and machine learning. Despite their rich structure and…

机器学习 · 统计学 2023-03-02 Sloan Nietert , Rachel Cummings , Ziv Goldfeld

The sliced Wasserstein metric compares probability measures on $\mathbb{R}^d$ by taking averages of the Wasserstein distances between projections of the measures to lines. The distance has found a range of applications in statistics and…

偏微分方程分析 · 数学 2024-11-25 Sangmin Park , Dejan Slepčev

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

We study the estimation and concentration on its expectation of the probability to observe data further than a specified distance from a given iid sample in a metric space. The problem extends the classical problem of estimation of the…

统计理论 · 数学 2022-11-23 Andreas Maurer

The Gromov-Wasserstein (GW) distance is frequently used in machine learning to compare distributions across distinct metric spaces. Despite its utility, it remains computationally intensive, especially for large-scale problems. Recently, a…

机器学习 · 统计学 2024-10-01 Antoine Salmona , Julie Delon , Agnès Desolneux

Understanding the space of probability measures on a metric space equipped with a Wasserstein distance is one of the fundamental questions in mathematical analysis. The Wasserstein metric has received a lot of attention in the machine…

机器学习 · 计算机科学 2021-03-02 Arijit Sehanobish , Neal Ravindra , David van Dijk

1. Complex systems of moving and interacting objects are ubiquitous in the natural and social sciences. Predicting their behavior often requires models that mimic these systems with sufficient accuracy, while accounting for their inherent…

定量方法 · 定量生物学 2014-12-02 Jonathan R. Potts , Marie Auger-Méthé , Karl Mokross , Mark A. Lewis

The Wasserstein metric or earth mover's distance (EMD) is a useful tool in statistics, machine learning and computer science with many applications to biological or medical imaging, among others. Especially in the light of increasingly…

最优化与控制 · 数学 2018-01-26 Jörn Schrieber , Dominic Schuhmacher , Carsten Gottschlich

This work characterizes, analytically and numerically, two major effects of the quadratic Wasserstein ($W_2$) distance as the measure of data discrepancy in computational solutions of inverse problems. First, we show, in the…

数值分析 · 数学 2020-06-24 Bjorn Engquist , Kui Ren , Yunan Yang

We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any…

机器学习 · 计算机科学 2017-11-21 Yukun Chen , Jianbo Ye , Jia Li

In this note, we propose an extension of the Wasserstein 1-metric ($W_1$) for matrix probability densities, matrix-valued density measures, and an unbalanced interpretation of mass transport. The key is using duality theory, in particular,…

泛函分析 · 数学 2017-03-07 Yongxin Chen , Tryphon T. Georgiou , Lipeng Ning , Allen Tannenbaum

We revisit Markowitz's mean-variance portfolio selection model by considering a distributionally robust version, where the region of distributional uncertainty is around the empirical measure and the discrepancy between probability measures…

统计方法学 · 统计学 2018-02-15 Jose Blanchet , Lin Chen , Xun Yu Zhou

Wasserstein Discriminant Analysis (WDA) is a new supervised method that can improve classification of high-dimensional data by computing a suitable linear map onto a lower dimensional subspace. Following the blueprint of classical Linear…

机器学习 · 统计学 2018-09-21 Rémi Flamary , Marco Cuturi , Nicolas Courty , Alain Rakotomamonjy