Spectral Diffusion Processes
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.
Cite
Text
Phillips et al. "Spectral Diffusion Processes." NeurIPS 2022 Workshops: SBM, 2022.Markdown
[Phillips et al. "Spectral Diffusion Processes." NeurIPS 2022 Workshops: SBM, 2022.](https://mlanthology.org/neuripsw/2022/phillips2022neuripsw-spectral/)BibTeX
@inproceedings{phillips2022neuripsw-spectral,
title = {{Spectral Diffusion Processes}},
author = {Phillips, Angus and Seror, Thomas and Hutchinson, Michael John and De Bortoli, Valentin and Doucet, Arnaud and Mathieu, Emile},
booktitle = {NeurIPS 2022 Workshops: SBM},
year = {2022},
url = {https://mlanthology.org/neuripsw/2022/phillips2022neuripsw-spectral/}
}