Flow Matching on Symmetric Spaces

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ruscelli, Francesco, Zanchetta, Ferdinando, Fioresi, Rita
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914530868592640
author Ruscelli, Francesco
Zanchetta, Ferdinando
Fioresi, Rita
author_facet Ruscelli, Francesco
Zanchetta, Ferdinando
Fioresi, Rita
contents We introduce a general framework for training flow matching models on Riemannian symmetric spaces, a large class of manifolds that includes the sphere, hyperbolic space and Grassmannians. We exploit their algebraic structure to reformulate flow matching on symmetric spaces as flow matching on a subspace of the Lie algebra of their isometry group, thus linearizing the problem and greatly simplifying the handling of geodesics. As an application, we showcase our framework on the real Grassmannians $\operatorname{SO}(n) / \operatorname{SO}(k) \times \operatorname{SO}(n-k)$.
format Preprint
id arxiv_https___arxiv_org_abs_2605_03588
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Flow Matching on Symmetric Spaces
Ruscelli, Francesco
Zanchetta, Ferdinando
Fioresi, Rita
Machine Learning
Artificial Intelligence
68T07
We introduce a general framework for training flow matching models on Riemannian symmetric spaces, a large class of manifolds that includes the sphere, hyperbolic space and Grassmannians. We exploit their algebraic structure to reformulate flow matching on symmetric spaces as flow matching on a subspace of the Lie algebra of their isometry group, thus linearizing the problem and greatly simplifying the handling of geodesics. As an application, we showcase our framework on the real Grassmannians $\operatorname{SO}(n) / \operatorname{SO}(k) \times \operatorname{SO}(n-k)$.
title Flow Matching on Symmetric Spaces
topic Machine Learning
Artificial Intelligence
68T07
url https://arxiv.org/abs/2605.03588