We provide theoretical convergence guarantees for score-based generative models (SGMs)
such as denoising diffusion probabilistic models (DDPMs), which constitute the backbone of …

We give an improved theoretical analysis of score-based generative modeling. Under a
score estimate with small $ L^ 2$ error (averaged across timesteps), we provide efficient …

Score-based generative modeling (SGM) is a highly successful approach for learning a
probability distribution from data and generating further samples. We prove the first …

We develop a framework for non-asymptotic analysis of deterministic samplers used for
diffusion generative modeling. Several recent works have analyzed stochastic samplers …

ABSTRACT Statisticians often use Monte Carlo methods to approximate probability
distributions, primarily with Markov chain Monte Carlo and importance sampling. Sequential …

Diffusion models are a powerful method for generating approximate samples from high-
dimensional data distributions. Several recent results have provided polynomial bounds on …

Classically, the continuous-time Langevin diffusion converges exponentially fast to its
stationary distribution π under the sole assumption that π satisfies a Poincaré inequality …

Abstract Along with Markov chain Monte Carlo (MCMC) methods, variational inference (VI)
has emerged as a central computational approach to large-scale Bayesian inference …

For the task of sampling from a density $\pi\propto\exp (-V) $ on $\R^ d $, where $ V $ is
possibly non-convex but $ L $-gradient Lipschitz, we prove that averaged Langevin Monte …

It is a fundamental problem to understand the complexity of high-accuracy sampling from a
strongly log-concave density π on ℝ d. Indeed, in practice, high-accuracy samplers such as …