Timezone: »

 
Spectral Diffusion Processes
Angus Phillips · Thomas Seror · Michael Hutchinson · Valentin De Bortoli · Arnaud Doucet · Emile Mathieu

@
in NeurIPS 2022 Workshop on Score-Based Methods »
Event URL: https://openreview.net/forum?id=bOmLb2i0W_h »

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.

Author Information

Angus Phillips (University of Oxford)
Thomas Seror (École Normale Supérieure - PSL)
Michael Hutchinson (University of Oxford)

Hi I'm Michael, a first year DPhil student at Oxford under the supervision of Yee Whye Teh and Max Welling. I'm interested in Probabalistic Machine Leanring in general, with a specific interests in distributed learning, generative modelling and uncertianty at a functional level.

Valentin De Bortoli (ENS Ulm, CNRS)
Arnaud Doucet (Oxford)
Emile Mathieu (University of Cambridge)

More from the Same Authors