Wasserstein Barycenters over Riemannian manifolds
By Young-Heon Kim, Brendan Pass. 2014
96 citations recorded by the source corpus.
We study barycenters in the space of probability measures on a Riemannian manifold, equipped with the Wasserstein metric. Under reasonable assumptions, we establish absolute continuity of the barycenter of general measures $\Omega \in P(P(M))$ on Wasserstein space, extending on one hand, results in the Euclidean case (for barycenters between finitely many measures) of Agueh and Carlier \cite{ac} to the Riemannian setting, and on the other hand, results in the Riemannian case of Cordero-Erausquin, McCann, Schmuckenschl\"ager \cite{c-ems} for barycenters between two measures to the multi-marginal setting. Our work also extends these results to the case where $\Omega$ is not finitely supported. As applications, we prove versions of Jensen's inequality on Wasserstein space and a generalized Brunn-Minkowski inequality for a random measurable set on a Riemannian manifold.
Subfields: Applied Mathematics, Geometry and Topology
View Paper: https://www.semanticscholar.org/paper/66aaada46aadd436d73d9a2a2f147ea45f174b97
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Applied Mathematics
- Julio D. Backhoff Veraguas
- Joaquín Fontbona
- Felipe A. Tobar
- Gonzalo Rios
- Thierry Klein
- Jérémie Bigot
In Geometry and Topology
- Thierry Klein
- Joaquín Fontbona
- Felipe A. Tobar
- Jérémie Bigot
- Gonzalo Rios
- Julio D. Backhoff Veraguas
Citations in the corpus
- Consistent estimation of a population barycenter in the Wasserstein space (2013, background): “Some generalization of the results in [31] for probability measures defined on a Riemannian manifold, equipped with the Wasserstein metric, have been recently proposed in [30].”
- Characterization of barycenters in the Wasserstein space by averaging optimal transport maps (2012, background): “Some generalization of these notions for probability measures defined on a Riemannian manifold, equipped with the Wasserstein metric, have been recently proposed in [34] and [33].”
- Bayesian Learning with Wasserstein Barycenters (2018, background): “Let us now recall the Wasserstein barycenter, introduced in [1] and further studied in [35, 25, 28], among others.”