BriefGPT.xyz
May, 2024
在基于评分扩散模型中适应未知的低维结构
Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
HTML
PDF
Gen Li, Yuling Yan
TL;DR
本研究通过设计独特的系数,首次理论证明了去噪扩散概率模型可以适应目标分布中未知的低维结构,凸显了系数设计的重要性。
Abstract
This paper investigates score-based
diffusion models
when the underlying target distribution is concentrated on or near
low-dimensional manifolds
within the higher-dimensional space in which they formally reside,
→