Séance Séminaire

Séminaire de Probabilités et Statistique

Concentration of empirical barycenters in metric spaces

arycenters in non-Euclidean geometries are the most natural extension of linear averaging. They are widely used in shape statistics, optimal transport and matrix analysis. In this talk, I will present their asymptotic properties, such as law of large numbers and central limit theorem. I will also present some more recent results about their non-asymptotic concentration rate.