English

Hyperbolic Sliced-Wasserstein via Geodesic and Horospherical Projections

Machine Learning 2023-06-27 v2 Methodology Machine Learning

Abstract

It has been shown beneficial for many types of data which present an underlying hierarchical structure to be embedded in hyperbolic spaces. Consequently, many tools of machine learning were extended to such spaces, but only few discrepancies to compare probability distributions defined over those spaces exist. Among the possible candidates, optimal transport distances are well defined on such Riemannian manifolds and enjoy strong theoretical properties, but suffer from high computational cost. On Euclidean spaces, sliced-Wasserstein distances, which leverage a closed-form of the Wasserstein distance in one dimension, are more computationally efficient, but are not readily available on hyperbolic spaces. In this work, we propose to derive novel hyperbolic sliced-Wasserstein discrepancies. These constructions use projections on the underlying geodesics either along horospheres or geodesics. We study and compare them on different tasks where hyperbolic representations are relevant, such as sampling or image classification.

Keywords

Cite

@article{arxiv.2211.10066,
  title  = {Hyperbolic Sliced-Wasserstein via Geodesic and Horospherical Projections},
  author = {Clément Bonet and Laetitia Chapel and Lucas Drumetz and Nicolas Courty},
  journal= {arXiv preprint arXiv:2211.10066},
  year   = {2023}
}

Comments

Accepted at the TAG-ML 2023 ICML Workshop

R2 v1 2026-06-28T06:11:16.274Z