UNIVERSITY
OF WROC£AW
 
Main Page
Contents
Online First
General Information
Instructions for authors


VOLUMES
44.1 43.2 43.1 42.2 42.1 41.2 41.1
40.2 40.1 39.2 39.1 38.2 38.1 37.2
37.1 36.2 36.1 35.2 35.1 34.2 34.1
33.2 33.1 32.2 32.1 31.2 31.1 30.2
30.1 29.2 29.1 28.2 28.1 27.2 27.1
26.2 26.1 25.2 25.1 24.2 24.1 23.2
23.1 22.2 22.1 21.2 21.1 20.2 20.1
19.2 19.1 18.2 18.1 17.2 17.1 16.2
16.1 15 14.2 14.1 13.2 13.1 12.2
12.1 11.2 11.1 10.2 10.1 9.2 9.1
8 7.2 7.1 6.2 6.1 5.2 5.1
4.2 4.1 3.2 3.1 2.2 2.1 1.2
1.1
 
 
WROC£AW UNIVERSITY
OF SCIENCE AND
TECHNOLOGY

Contents of PMS, Vol. 41, Fasc. 2,
pages 237 - 265
DOI: 10.37190/0208-4147.41.2.3
Published online 11.8.2021
 

On optimal matching of Gaussian samples III

Michel Ledoux
Jie-Xiang Zhu

Abstract:

This article is a continuation of M. Ledoux papers 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 independent random variables \(X_1, \ldots, X_n\) with common distribution the standard Gaussian measure \(\mu\) on \(R^d\), \(d \geq 3\), and \(\mu_n = \frac 1n \sum_{i=1}^n \delta_{X_i}\) the associated empirical measure, \[E [ \mathrm {W}_p^p (\mu_n , \mu )] \approx \frac {1}{n^{p/d}}\] for any \(1 \leq p < d\), where \(\mathrm {W}_p\) is the \(p\)th Kantorovich–Wasserstein metric. That is, in this range, the rates are the same as in the uniform case. The proof relies on the pde and mass transportation approach developed by L. Ambrosio, F. Stra and D. Trevisan in a compact setting.

2010 AMS Mathematics Subject Classification: Primary 60D05, 60F25; Secondary 60H15, 49J55, 58J35.

Keywords and phrases: optimal matching, empirical measure, optimal transport, Gaussian sample, Mehler kernel.

M. Ajtai, J. Komlós and G. Tusnády, On optimal matchings, Combinatorica 4 (1984), 259-264.

L. Ambrosio, F. Stra and D. Trevisan, A PDE approach to a 2-dimensional matching problem, Probab. Theory Related Fields 173 (2019), 433-478.

D. Bakry, Étude des transformations de Riesz sur les variétés riemanniennes à  courbure de Ricci minorée, in: Séminaire de Probabilités XXI, Lecture Notes in Math. 1247, Springer, 1987, 137-172.

D. Bakry, I. Gentil and M. Ledoux, Analysis and Geometry of Markov Diffusion Operators, Grundlehren Math. Wiss. 348, Springer, 2014.

P. Berthet and J. Fort, Exact rate of convergence of the expected W2 distance between the empirical and true Gaussian distribution, Electron. J. Probab. 25 (2020), art. 12, 16 pp.

S. Bobkov and M. Ledoux, One-dimensional empirical measures, order statistics, and Kantorovich transport distances, Mem. Amer. Math. Soc. 261 (2019), no. 1259, v+126 pp.

S. Caracciolo, M. D'Achille and G. Sicuro, Anomalous scaling of the optimal cost in the one-dimensional random assignment problem, J. Statist. Phys. 174 (2019), 846-864.

S. Dereich, M. Scheutzow and R. Schottstedt, Constructive quantization: approximation by empirical measures, Ann. Inst. H. Poincaré Probab. Statist. 49 (2013), 1183-1203.

N. Fournier and A. Guillin, On the rate of convergence in Wasserstein distance of the empirical measure, Probab. Theory Related Fields 162 (2015), 707-738.

M. Ledoux, On optimal matching of Gaussian samples, Zap. Nauchn. Sem. S.-Peterburg. Otdel. Mat. Inst. Steklova 457 (2017), 226-264.

M. Ledoux, On optimal matching of Gaussian samples II, 2018.

P.-A. Meyer, Transformations de Riesz pour les lois gaussiennes, in: Séminaire de Probabilités XV, Lecture Notes in Math. 1059, Springer, 1984, 179-193.

R. Peyre, Comparison between W2 distance and L-1 norm, and localization of Wasserstein distance, ESAIM Control Optim. Calc. Var. 24 (2018), 1489-1501.

H. P. Rosenthal, On the subspaces of Lp (p„>„2) spanned by sequences of independent random variables, Israel J. Math. 8 (1970), 273-303.

F. Santambrogio, Optimal Transport for Applied Mathematicians, Progr. Nonlinear Differential Equations Appl. 87, Birkhäuser, 2015.

M. Talagrand, Upper and Lower Bounds of Stochastic Processes, Ergeb. Math. Grenzgeb. 60, Springer, 2014.

M. Talagrand, Scaling and non-standard matching theorems, C. R. Math. Acad. Sci. Paris  356 (2018), 692-695.

C. Villani, Optimal Transport: Old and New, Grundlehren Math. Wiss. 338, Springer, 2009.

J. Yukich, Some generalizations of the Euclidean two-sample matching problem, in: Probability in Banach Spaces 8, Progr. Probab. 30, Birkhäuser, 1992, 55-66.

Download:    Abstract    Full text