Busemann Functions in the Wasserstein Space: Existence, Closed-Forms, and Applications to Slicing

Clément Bonet, Elsa Cazelles, Lucas Drumetz, Nicolas Courty

TL;DR: We investigat how to compute the Busemann functon on the Wasserstein space, and use it to define sliced-Wasserstein distances between mixtures.

Abstract: The Busemann function has recently found many interests in a variety of geometric machine learning problems, as it naturally defines projections onto geodesic rays of Riemannian manifolds and generalizes the notion of hyperplanes. As several sources of data can be conveniently modeled as probability distributions, it is natural to study this function in the Wasserstein space, which carries a rich formal Riemannian structure induced by Optimal Transport metrics. In this work, we investigate the existence and computation of Busemann functions in Wasserstein space, which admits geodesic rays. We establish closed-form expressions in two important cases: one-dimensional distributions and Gaussian measures. These results enable explicit projection schemes for probability distributions on $\mathbb{R}$, which in turn allow us to define novel Sliced-Wasserstein distances over Gaussian mixtures and labeled datasets. We demonstrate the efficiency of those original schemes on synthetic datasets as well as transfer learning problems.

Code Dataset Promise: Yes

Code Dataset Url: https://github.com/clbonet/Busemann_Functions_in_the_Wasserstein_Space

Format Confirmation: I agree that I have read and followed the formatting instructions for the camera ready version.

Submission Number: 849