Characterization of barycenters in the Wasserstein space by averaging optimal transport maps

Abstract

This paper is concerned by the study of barycenters for random probability measures in the Wasserstein space. Using a duality argument, we give a precise characterization of the population barycenter for various parametric classes of random probability measures with compact support. In particular, we make a connection between averaging in the Wasserstein space as introduced in Agueh and Carlier (2011), and taking the expectation of optimal transport maps with respect to a fixed reference measure. We also discuss the usefulness of this approach in statistics for the analysis of deformable models in signal and image processing. In this setting, the problem of estimating a population barycenter from n independent and identically distributed random probability measures is also considered.

References in corpus (3)

• Semi-parametric estimation of shifts
• A deconvolution approach to estimation of a common shape in a shifted curves model
• Semiparametric curve alignment and shift density estimation for biological data

Cited by in corpus (9)

• Statistical Aspects of Wasserstein Distances
• Obtaining fairness using optimal transport theory
• Construction of Non-asymptotic Confidence Sets in 2-Wasserstein Space
• A Smoothed Dual Approach for Variational Wasserstein Problems
• Wide Consensus for Parallelized Inference
• Entropic Wasserstein Gradient Flows
• Discrete Wasserstein Barycenters: Optimal Transport for Discrete Data
• Iterative Bregman Projections for Regularized Transportation Problems
• Stochastic Approximation versus Sample Average Approximation for population Wasserstein barycenters