Metraipolis › archive › dc_786c3bc418a4
Light Entropic Optimal Transport on Riemannian Manifolds — arXiv:2610.03085
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03085
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:10:08.109Z
- SHA-256 of the archived text
88a98c2f5808913ba59f841e35ecf2e3169490116a58ba7ca52ec97370ad6882- Stable URL of this page
https://metraipolis.com/documento/dc_786c3bc418a4
How to cite
Light Entropic Optimal Transport on Riemannian Manifolds — arXiv:2610.03085 — arXiv, https://arxiv.org/abs/2610.03085 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_786c3bc418a4 (Metraipolis archive dc_786c3bc418a4, sha256 88a98c2f5808913ba59f841e35ecf2e3169490116a58ba7ca52ec97370ad6882)
BibTeX
@misc{dc786c3bc418a4,
title = {Light Entropic Optimal Transport on Riemannian Manifolds — arXiv:2610.03085},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03085},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_786c3bc418a4; sha256 88a98c2f5808913ba59f841e35ecf2e3169490116a58ba7ca52ec97370ad6882},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03085. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Entropic Optimal Transport (EOT) has become a practical framework for learning stochastic couplings between complex distributions, with applications in generative modeling and domain adaptation. However, most EOT solvers are designed for Euclidean spaces, while manifold extensions remain limited and often rely on costly iterative methods, simulated dynamics, or generic neural models that do not fully exploit the underlying geometry. We introduce ManifoldLightOT, a light approach for learning kernel-induced EOT couplings directly on common manifolds. Using the kernel form of the EOT solution, we construct geometry-specific Gibbs kernels together with compatible potential parameterizations for spheres, tori, $\mathrm{SO}(3)$, and $\mathrm{SE}(3)$. These choices yield closed-form normalization and directly sampleable conditional distributions. Our formulation naturally extends to products of manifolds, making it applicable to more complex geometries. The parameters of the potentials are optimized directly from samples using Monte Carlo estimates of the learning objective. Through synthetic and real-world experiments, we show that ManifoldLightOT often outperforms existing manifold OT methods while retaining direct sampling.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.03085 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T23:01:38.670Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).