Riemannian Diffusion Schrödinger Bridge [article]

James Thornton, Michael Hutchinson, Emile Mathieu, Valentin De Bortoli, Yee Whye Teh, Arnaud Doucet
2022 arXiv   pre-print
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
more » ... s. To overcome these issues, we introduce Riemannian Diffusion Schrödinger Bridge. Our proposed method generalizes Diffusion Schrödinger Bridge introduced in 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.
arXiv:2207.03024v1 fatcat:rdeza3l6ynbyzje7tvqctrgny4