Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions 事件

Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions arXiv:2409.02426v5 Announce Type: replace-cross Abstract: Despite their empirical success across a wide range of generative tasks, the fundamental principles underlying the ability of diffusion models to learn data distributions are poorly understood. In this work, we develop a new mathematical framework that explains how diffusion models can effectively learn low-dimensional distributions fro