Convergence of denoising diffusion models under the manifold hypothesis

08/10/2022
by   Valentin De Bortoli, et al.
0

Denoising diffusion models are a recent class of generative models exhibiting state-of-the-art performance in image and audio synthesis. Such models approximate the time-reversal of a forward noising process from a target distribution to a reference density, which is usually Gaussian. Despite their strong empirical results, the theoretical analysis of such models remains limited. In particular, all current approaches crucially assume that the target density admits a density w.r.t. the Lebesgue measure. This does not cover settings where the target distribution is supported on a lower-dimensional manifold or is given by some empirical distribution. In this paper, we bridge this gap by providing the first convergence results for diffusion models in this more general setting. In particular, we provide quantitative bounds on the Wasserstein distance of order one between the target data distribution and the generative distribution of the diffusion model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/27/2023

Diffusion Schrödinger Bridges for Bayesian Computation

Denoising diffusion models are a novel class of generative models that h...
research
08/09/2023

Do Diffusion Models Suffer Error Propagation? Theoretical Analysis and Consistency Regularization

While diffusion models have achieved promising performances in data synt...
research
03/03/2023

Diffusion Models are Minimax Optimal Distribution Estimators

While efficient distribution learning is no doubt behind the groundbreak...
research
02/20/2023

Unsupervised Out-of-Distribution Detection with Diffusion Inpainting

Unsupervised out-of-distribution detection (OOD) seeks to identify out-o...
research
06/08/2023

Interpreting and Improving Diffusion Models Using the Euclidean Distance Function

Denoising is intuitively related to projection. Indeed, under the manifo...
research
11/07/2022

From Denoising Diffusions to Denoising Markov Models

Denoising diffusions are state-of-the-art generative models which exhibi...
research
08/23/2023

Score diffusion models without early stopping: finite Fisher information is all you need

Diffusion models are a new class of generative models that revolve aroun...

Please sign up or login with your details

Forgot password? Click here to reset