Stochastic Wasserstein Barycenters

Author name not available (Why is that?)

Publication date: 15 February 2018

Abstract: We present a stochastic algorithm to compute the barycenter of a set of probability distributions under the Wasserstein metric from optimal transport. Unlike previous approaches, our method extends to continuous input distributions and allows the support of the barycenter to be adjusted in each iteration. We tackle the problem without regularization, allowing us to recover a sharp output whose support is contained within the support of the true barycenter. We give examples where our algorithm recovers a more meaningful barycenter than previous work. Our method is versatile and can be extended to applications such as generating super samples from a given distribution and recovering blue noise approximations.

Has companion code repository: https://github.com/gparracl/StochasticWassersteinBarycenter

This page was built for publication: Stochastic Wasserstein Barycenters

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6297824)