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

Jérémie Bigot (1) , Thierry Klein (2)

1 IMB - Institut de Mathématiques de Bordeaux
2 IMT - Institut de Mathématiques de Toulouse UMR5219

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.

Mots clés: Wasserstein space; Empirical and population barycenters; Fréchet mean; Convergence of random variables; Optimal transport; Curve and image warping; Deformable models

Domaines: Théorie [stat.TH]

Jérémie Bigot, Thierry Klein. Characterization of barycenters in the Wasserstein space by averaging optimal transport maps. 2015. ⟨hal-00763668v5⟩