A Central Limit Theorem for Semidiscrete Wasserstein Distances

arXiv2105.11721MaRDI QIDQ6368459FDOQ6368459

Authors: Eustasio Del Barrio, Alberto González Sanz, Jean-Michel Loubes 

Publication date: 25 May 2021

Abstract: We address the problem of proving a Central Limit Theorem for the empirical optimal transport cost, $sqrtnmathcal{T}_c(P_n,Q)-mathcal{W}_c(P,Q)$, in the semi discrete case, i.e when the distribution $P$ is finitely supported. We show that the asymptotic distribution is the supremun of a centered Gaussian process which is Gaussian under some additional conditions on the probability $Q$ and on the cost. Such results imply the central limit theorem for the $p$-Wassertein distance, for $pgeq1$. Finally, the semidiscrete framework provides a control on the second derivative of the dual formulation, which yields the first central limit theorem for the optimal transport potentials.

This page was built for publication: A Central Limit Theorem for Semidiscrete Wasserstein Distances

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6368459)