← ALB News · curated headline

Support recovery of diffusion models under the manifold hypothesis

arXiv Mathematics · WORLD · Mathematics · 11/17/2026, 12:00:00 AM

arXiv:2611.18738v1 Announce Type: new Abstract: We study diffusion models under the manifold hypothesis with possibly large score estimation and discretization errors, and show that while they may not exactly recover the data distribution, they will exactly recover the support (or data manifold). In continuous time, we use a Lyapunov function to show that even if the relative score estimation error is fixed (and not necessarily vanishing), then the rate at which the process approaches the support is $O(\sqrt{(T-t)|\log(T-t)|})$ as $t \to T$, where $T$ is the final time. In discrete time, we use geometric time steps with a fixed (non-vanishing) ratio and show that with a fixed (also not small) relative score estimation error, the process approaches the data manifold exponentially with the number of iterations. The proof relies on controlling a Gaussian measure of a neighborhood of the cut-locus of the data manifold, using a polynomial approximation argument combined with quantitative semi-algebraic estimates.

Continue to arXiv Mathematics →

You are being forwarded in 6s — stay on this page