Diffusion Score Estimation with Shallow Neural Networks: Regularity, Approximation, and Finite-Sample Rates
arXiv:2610.27206v1 Announce Type: new Abstract: We study the sample complexity of estimating Ornstein--Uhlenbeck diffusion scores in $\mathbb R^d$ using denoising score matching (DSM) with finite-width shallow ReLU networks, and its implications for reverse-process sampling. Under weak differentiab…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-21 04:00 · arXiv stat.ML
Diffusion Score Estimation with Shallow Neural Networks: Regularity, Approximation, and Finite-Sample Rates