Diffusion-Augmented Neural Processes
Machine Learning
2023-11-17 v1
Abstract
Over the last few years, Neural Processes have become a useful modelling tool in many application areas, such as healthcare and climate sciences, in which data are scarce and prediction uncertainty estimates are indispensable. However, the current state of the art in the field (AR CNPs; Bruinsma et al., 2023) presents a few issues that prevent its widespread deployment. This work proposes an alternative, diffusion-based approach to NPs which, through conditioning on noised datasets, addresses many of these limitations, whilst also exceeding SOTA performance.
Cite
@article{arxiv.2311.09848,
title = {Diffusion-Augmented Neural Processes},
author = {Lorenzo Bonito and James Requeima and Aliaksandra Shysheya and Richard E. Turner},
journal= {arXiv preprint arXiv:2311.09848},
year = {2023}
}
Comments
Accepted to the NeurIPS 2023 Workshop on Diffusion Models