Regularized Barycenters in the Wasserstein Space
Langue
en
Communication dans un congrès
Ce document a été publié dans
Lecture Notes in Computer Science, Lecture Notes in Computer Science, 3rd International Conference Geometric Science of Information (GSI'17), 2017-11-07, Paris. 2017, vol. 10589, p. 83-90
Springer International Publishing
Résumé en anglais
This paper is an overview of results that have been obtain in [J. Bigot, E. Cazelles, and N. Papadakis. Penalized barycenters in the Wasserstein space. Submitted. Available at https://128.84.21.199/abs/1606.010252] on the ...Lire la suite >
This paper is an overview of results that have been obtain in [J. Bigot, E. Cazelles, and N. Papadakis. Penalized barycenters in the Wasserstein space. Submitted. Available at https://128.84.21.199/abs/1606.010252] on the convex regularization of Wasserstein barycenters for random measures supported on Rd. We discuss the existence and uniqueness of such barycenters for a large class of regularizing functions. A stability result of regularized barycenters in terms of Bregman distance associated to the convex regularization term is also given. Additionally we discuss the convergence of the regularized empirical barycenter of a set of n iid random probability measures towards its population counterpart in the real line case, and we discuss its rate of convergence. This approach is shown to be appropriate for the statistical analysis of discrete or absolutely continuous random measures. In this setting, we propose an efficient minimization algorithm based on accelerated gradient descent for the computation of regularized Wasserstein barycenters.< Réduire
Mots clés en anglais
Wasserstein space
Fréchet mean
Barycenter of probability measures
Convex regularization
Bregman divergence
Project ANR
Generalized Optimal Transport Models for Image processing - ANR-16-CE33-0010
Origine
Importé de halUnités de recherche