On optimal matching of Gaussian samples. III

DOI10.37190/0208-4147.41.2.3MaRDI QIDQ5029382zbMATH OpenOpenAlexFDO

Authors

Publication date 14 February 2022

Published in Probability and Mathematical Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1911.07579

zbMATH Keywords

empirical measureGaussian sampleMehler kerneloptimal matchingoptimal transport

Mathematics Subject Classification ID

Existence of optimal solutions to problems involving randomness (49J55) Optimal transportation (49Q22) Heat and other parabolic equation methods for PDEs on manifolds (58J35) Geometric probability and stochastic geometry (60D05) (L^p)-limit theorems (60F25) Stochastic partial differential equations (aspects of stochastic analysis) (60H15)

Abstract: This article is a continuation of the papers [8,9] in which the optimal matching problem, and the related rates of convergence of empirical measures for Gaussian samples are addressed. A further step in both the dimensional and Kantorovich parameters is achieved here, proving that, given $X_1,ldots,X_n$ independent random variables with common distribution the standard Gaussian measure $mu$ on $mathbb{R}^d$, $dgeq3$, and $m{u}_n,=,frac1nsu{m}_{i=1}^{n}delt{a}_{X_i}$ the associated empirical measure, ${\displaystyle }$ mathbb{E} �ig( mathrm {W}_p^p (mu_n , mu )�ig ) , approx , frac {1}{n^{p/d}} ${\displaystyle }$ for any $1leqp<d$, where $mathrm{W}_p$ is the $p$-th Kantorovich metric. The proof relies on the pde and mass transportation approach developed by L. Ambrosio, F. Stra and D. Trevisan in a compact setting.

Recommendations

• On optimal matching of Gaussian samples
• Optimal Matching and Empirical Measures
• Exact rate of convergence of the expected \(W_2\) distance between the empirical and true Gaussian distribution
• Asymptotics for transportation cost in high dimensions
• Limit laws of the empirical Wasserstein distance: Gaussian distributions

Cites work

• A PDE approach to a 2-dimensional matching problem
• Analysis and geometry of Markov diffusion operators
• Anomalous scaling of the optimal cost in the one-dimensional random assignment problem
• Comparison between \(W_2\) distance and \(\dot{H}^{-1}\) norm, and localization of Wasserstein distance
• Constructive quantization: approximation by empirical measures
• Exact rate of convergence of the expected \(W_2\) distance between the empirical and true Gaussian distribution
• scientific article; zbMATH DE number 434648 (Why is no real title available?)
• scientific article; zbMATH DE number 3864243 (Why is no real title available?)
• scientific article; zbMATH DE number 4024348 (Why is no real title available?)
• On optimal matchings
• On the rate of convergence in Wasserstein distance of the empirical measure
• On the subspaces of \(L^p\) \((p > 2)\) spanned by sequences of independent random variables
• One-dimensional empirical measures, order statistics, and Kantorovich transport distances
• Optimal Transport
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• Scaling and non-standard matching theorems
• Upper and lower bounds for stochastic processes. Modern methods and classical problems

Cited in

(14)

• Rates of convergence for partial mass problems
• Wasserstein asymptotics for the empirical measure of fractional Brownian motion on a flat torus
• Exact rate of convergence of the expected \(W_2\) distance between the empirical and true Gaussian distribution
• On optimal matching of Gaussian samples
• One-dimensional empirical measures, order statistics, and Kantorovich transport distances
• Optimal Matching of Random Samples and Rates of Convergence of Empirical Measures
• Optimal transport methods for combinatorial optimization over two random point sets
• Random matching in 2D with exponent 2 for Gaussian densities
• Annealed quantitative estimates for the quadratic 2D-discrete random matching problem
• Optimal sequencing depth for single-cell RNA-sequencing in Wasserstein space
• Asymptotics of Kantorovich distance for empirical measures of the Laguerre model
• Convergence of empirical optimal transport in unbounded settings
• Wasserstein asymptotics for Brownian motion on the flat torus and Brownian interlacements
• Almost sharp rates of convergence for the average cost and displacement in the optimal matching problem

This page was built for publication: On optimal matching of Gaussian samples. III

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5029382)