On the rate of convergence of empirical measures in $\infty$-transportation distance

We consider random i.i.d. samples of absolutely continuous measures on bounded connected domains. We prove an upper bound on the $\infty$-transportation distance between the measure and the empirical measure of the sample. The bound is optimal in terms of scaling with the number of sample points.

[1]  H. Chernoff.  A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations , 1952 .

[2]  R. Dudley.  The Speed of Mean Glivenko-Cantelli Convergence , 1969 .

[3]  János Komlós,et al.  On optimal matchings , 1984, Comb..

[4]  Frank Thomson Leighton,et al.  Tight bounds for minimax grid matching, with applications to the average case analysis of algorithms , 1986, STOC '86.

[5]  J. Yukich,et al.  Minimax Grid Matching and Empirical Measures , 1991 .

[6]  M. Talagrand,et al.  The Integrability of the Square Exponential Transportation Cost , 1993 .

[7]  M. Talagrand.  THE TRANSPORTATION COST FROM THE UNIFORM MEASURE TO THE EMPIRICAL MEASURE IN DIMENSION > 3 , 1994 .

[8]  J. Yukich,et al.  Asymptotics for transportation cost in high dimensions , 1995 .

[9]  C. Villani,et al.  Quantitative Concentration Inequalities for Empirical Measures on Non-compact Spaces , 2005, math/0503123.

[10]  M. Talagrand.  The Generic Chaining , 2005 .

[11]  Thierry Champion,et al.  The ∞-Wasserstein Distance: Local Solutions and Existence of Optimal Transport Maps , 2008, SIAM J. Math. Anal..

[12]  Emmanuel Boissard.  Simple Bounds for the Convergence of Empirical and Occupation Measures in 1-Wasserstein Distance , 2011, 1103.3188.

[13]  J. Ball,et al.  Partial regularity and smooth topology-preserving approximations of rough domains , 2013, 1312.5156.

[14]  M. Talagrand.  Upper and Lower Bounds for Stochastic Processes , 2021, Ergebnisse der Mathematik und ihrer Grenzgebiete. 3. Folge / A Series of Modern Surveys in Mathematics.