Back to Search Start Over

Spectral Diffusion Processes

Spectral Diffusion Processes

Authors :
Phillips, Angus
Seror, Thomas
Hutchinson, Michael
De Bortoli, Valentin
Doucet, Arnaud
Mathieu, Emile
Publication Year :
2022

Abstract

Score-based generative modelling (SGM) has proven to be a very effective method for modelling densities on finite-dimensional spaces. In this work we propose to extend this methodology to learn generative models over functional spaces. To do so, we represent functional data in spectral space to dissociate the stochastic part of the processes from their space-time part. Using dimensionality reduction techniques we then sample from their stochastic component using finite dimensional SGM. We demonstrate our method's effectiveness for modelling various multimodal datasets.<br />Comment: 17 pages, 11 figures, Score-based Method Workshop at 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2209.14125
Document Type :
Working Paper