Riemannian Diffusion Schr\"odinger Bridge - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Riemannian Diffusion Schr\"odinger Bridge

James Thornton
  • Fonction : Auteur
Michael Hutchinson
  • Fonction : Auteur
Emile Mathieu
  • Fonction : Auteur
Valentin de Bortoli
  • Fonction : Auteur
  • PersonId : 1084097
  • IdRef : 249460300
Yee Whye Teh
  • Fonction : Auteur
Arnaud Doucet
  • Fonction : Auteur

Résumé

Score-based generative models exhibit state of the art performance on density estimation and generative modeling tasks. These models typically assume that the data geometry is flat, yet recent extensions have been developed to synthesize data living on Riemannian manifolds. Existing methods to accelerate sampling of diffusion models are typically not applicable in the Riemannian setting and Riemannian score-based methods have not yet been adapted to the important task of interpolation of datasets. To overcome these issues, we introduce \emph{Riemannian Diffusion Schr\"odinger Bridge}. Our proposed method generalizes Diffusion Schr\"odinger Bridge introduced in \cite{debortoli2021neurips} to the non-Euclidean setting and extends Riemannian score-based models beyond the first time reversal. We validate our proposed method on synthetic data and real Earth and climate data.

Dates et versions

hal-03945472 , version 1 (18-01-2023)

Identifiants

Citer

James Thornton, Michael Hutchinson, Emile Mathieu, Valentin de Bortoli, Yee Whye Teh, et al.. Riemannian Diffusion Schr\"odinger Bridge. 2023. ⟨hal-03945472⟩
16 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More