Lorenzo BonitoJames RequeimaAliaksandra ShysheyaRichard E. Turner
Lorenzo BonitoJames RequeimaAliaksandra ShysheyaRichard E. Turner
Nov 2023
0被引用
1笔记
摘要原文
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.
