Linearized optimal transport on manifolds
Abstract
Optimal transport is a geometrically intuitive, robust and flexible metric for sample comparison in data analysis and machine learning. Its formal Riemannian structure allows for a local linearization via a tangent space approximation. This in turn leads to a reduction of computational complexity and simplifies combination with other methods that require a linear structure. Recently this approach has been extended to the unbalanced Hellinger--Kantorovich (HK) distance. In this article we further extend the framework in various ways, including measures on manifolds, the spherical HK distance, a study of the consistency of discretization via the barycentric projection, and the continuity properties of the logarithmic map for the HK distance.
Cite
@article{arxiv.2303.13901,
title = {Linearized optimal transport on manifolds},
author = {Clément Sarrazin and Bernhard Schmitzer},
journal= {arXiv preprint arXiv:2303.13901},
year = {2024}
}
Comments
45 pages, 10 figures Numerical examples can be generated using the code at https://gitlab.gwdg.de/bernhard.schmitzer/linot