
























Abstract:Diffusion models have become a leading framework in generative modeling, yet their theoretical understanding -- especially for high-dimensional data concentrated on low-dimensional structures -- remains incomplete. This paper investigates how diffusion models learn such structured data, focusing on two key aspects: statistical complexity and influence of data geometric properties. By modeling data as samples from a smooth Riemannian manifold, our analysis reveals crucial decompositions of score functions in diffusion models under different levels of injected noise. We also highlight the interplay of manifold curvature with the structures in the score function. These analyses enable an efficient neural network approximation to the score function, built upon which we further provide statistical rates for score estimation and distribution learning. Remarkably, the obtained statistical rates are governed by the intrinsic dimension of data and the manifold curvature. These results advance the statistical foundations of diffusion models, bridging theory and practice for generative modeling on manifolds.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2603.20645 [cs.LG] |
| (or arXiv:2603.20645v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2603.20645 arXiv-issued DOI via DataCite |
From: Zixuan Zhang [view email]
[v1]
Sat, 21 Mar 2026 04:40:19 UTC (1,872 KB)
[v2]
Tue, 28 Apr 2026 08:05:44 UTC (1,872 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。