Intrinsic Gaussian Vector Fields on Manifolds

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Robert-Nicoud, Daniel, Krause, Andreas, Borovitskiy, Viacheslav
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914735183626240
author Robert-Nicoud, Daniel
Krause, Andreas
Borovitskiy, Viacheslav
author_facet Robert-Nicoud, Daniel
Krause, Andreas
Borovitskiy, Viacheslav
contents Various applications ranging from robotics to climate science require modeling signals on non-Euclidean domains, such as the sphere. Gaussian process models on manifolds have recently been proposed for such tasks, in particular when uncertainty quantification is needed. In the manifold setting, vector-valued signals can behave very differently from scalar-valued ones, with much of the progress so far focused on modeling the latter. The former, however, are crucial for many applications, such as modeling wind speeds or force fields of unknown dynamical systems. In this paper, we propose novel Gaussian process models for vector-valued signals on manifolds that are intrinsically defined and account for the geometry of the space in consideration. We provide computational primitives needed to deploy the resulting Hodge-Matérn Gaussian vector fields on the two-dimensional sphere and the hypertori. Further, we highlight two generalization directions: discrete two-dimensional meshes and "ideal" manifolds like hyperspheres, Lie groups, and homogeneous spaces. Finally, we show that our Gaussian vector fields constitute considerably more refined inductive biases than the extrinsic fields proposed before.
format Preprint
id arxiv_https___arxiv_org_abs_2310_18824
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Intrinsic Gaussian Vector Fields on Manifolds
Robert-Nicoud, Daniel
Krause, Andreas
Borovitskiy, Viacheslav
Machine Learning
Various applications ranging from robotics to climate science require modeling signals on non-Euclidean domains, such as the sphere. Gaussian process models on manifolds have recently been proposed for such tasks, in particular when uncertainty quantification is needed. In the manifold setting, vector-valued signals can behave very differently from scalar-valued ones, with much of the progress so far focused on modeling the latter. The former, however, are crucial for many applications, such as modeling wind speeds or force fields of unknown dynamical systems. In this paper, we propose novel Gaussian process models for vector-valued signals on manifolds that are intrinsically defined and account for the geometry of the space in consideration. We provide computational primitives needed to deploy the resulting Hodge-Matérn Gaussian vector fields on the two-dimensional sphere and the hypertori. Further, we highlight two generalization directions: discrete two-dimensional meshes and "ideal" manifolds like hyperspheres, Lie groups, and homogeneous spaces. Finally, we show that our Gaussian vector fields constitute considerably more refined inductive biases than the extrinsic fields proposed before.
title Intrinsic Gaussian Vector Fields on Manifolds
topic Machine Learning
url https://arxiv.org/abs/2310.18824