Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions. (arXiv:2211.01916v1 [cs.LG])

In this paper, we focus on the theoretical analysis of diffusion-based
generative modeling. Under an $L^2$-accurate score estimator, we provide
convergence guarantees with polynomial complexity for any data distribution
with second-order moment, by either employing an early stopping technique or
assuming smoothness condition on the score function of the data distribution.
Our result does not rely on any log-concavity or functional inequality
assumption and has a logarithmic dependence on the smoothness. In particular,
we show that under only a finite …

analysis arxiv assumptions modeling