Metraipolis › archive › dc_aa4516d79261
When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds — arXiv:2609.25659
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25659
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T15:07:30.130Z
- SHA-256 of the archived text
e325cce1438b32c77c8d8aead9fa25dcb66634fab49dc0d558a78605d60a6542- Stable URL of this page
https://metraipolis.com/documento/dc_aa4516d79261
How to cite
When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds — arXiv:2609.25659 — arXiv (en), https://arxiv.org/abs/2609.25659 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa4516d79261 (Metraipolis archive dc_aa4516d79261, sha256 e325cce1438b32c77c8d8aead9fa25dcb66634fab49dc0d558a78605d60a6542)
BibTeX
@misc{dcaa4516d79261,
title = {When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds — arXiv:2609.25659},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25659},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa4516d79261; sha256 e325cce1438b32c77c8d8aead9fa25dcb66634fab49dc0d558a78605d60a6542},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25659. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many scientific datasets, such as molecular conformational ensembles or single-cell tissue measurements, are naturally modeled as meta-distributions: distributions over probability measures on non-Euclidean domains. Existing generative methods largely assume Euclidean geometry and fail to capture this structure. We introduce Riemannian Wasserstein Entropic Flow Matching (RWEFM), a generative framework on the Wasserstein space $\mathcal{P}_2(\mathcal{M})$ of a Riemannian manifold $(\mathcal{M},g)$. RWEFM is trained by regressing a neural vector field onto Riemannian optimal transport velocities, using McCann displacement interpolations as conditional paths. We confirm theoretically that this construction leads to a valid flow matching approach on $\mathcal{P}_2(\mathcal{M})$ and introduce the Riemannian Entropic Map, a GPU-efficient approximation of the optimal transport map on manifolds. Our experiments show that by respecting the intrinsic geometry of the data, RWEFM can generate whole single-cell samples in hyperspherical latent spaces and protein conformational ensembles on the torus. As RWEFM requires only a geodesic distance and a projection operator, it is not restricted to manifolds with closed-form geometry, which we demonstrate by generating distributions on a general triangulated mesh.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.25659 — 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 2026-10-08T14:37:29.405Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).