Riemannian Diffusion Schrödinger Bridge release_rdeza3l6ynbyzje7tvqctrgny4

by James Thornton, Michael Hutchinson, Emile Mathieu, Valentin De Bortoli, Yee Whye Teh, Arnaud Doucet

Released as a article .

2022  

Abstract

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 Riemannian Diffusion Schrödinger Bridge. Our proposed method generalizes Diffusion Schrödinger Bridge introduced in <cit.> 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.
In text/plain format

Archived Files and Locations

application/pdf  11.8 MB
file_yid7ojhivzex7iyahtjokzafem
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2022-07-07
Version   v1
Language   en ?
arXiv  2207.03024v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 5afa7d50-ff54-4514-8aec-8e7dcc8273f9
API URL: JSON