Marginal-constrained modified Wasserstein barycenters for Gaussian distributions and Gaussian mixtures
Résumé
The aim of this work is to propose modified Wasserstein barycenters for probability measures defined on cartesian product sets which satisfy given marginal constraints. We focus on the specific case of Gaussian and Gaussian mixture distributions, as the proposed approach strongly relies on new results about properties of geometric means of covariance matrices. Wasserstein barycenters that respect some desired constraints on the marginals of the distributions, both for Gaussian distributions and for mixtures of Gaussian distributions. In the case of Gaussian distributions, the marginal-constrained modified Wasserstein barycenters can be analytically computed, while for Gaussian mixtures, computing the marginal-constrained barycenter consists in a postprocessing of the Gaussian mixture Wasserstein barycenter. In both cases, we provide numerical simulations illustrating the difference between Wasserstein barycenters and modified marginal-constrained Wasserstein barycenters. We moreover provide several test cases where the marginal-constrained Wasserstein barycenters interpolate better than regular Wasserstein barycenters, showcasing the practical interest of the proposed approach. As a by-product, we prove new results concerning marginal-preserving Wasserstein barycenters. Indeed,} Wasserstein barycenters do not preserve marginals in general. In this work, as a consequence of the derived properties on the geometric mean of covariance matrices, we obtain sufficient and necessary conditions for the Wasserstein barycenter between two Gaussian distributions to preserve marginals, and provide necessary conditions in the case of more than two Gaussians.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |