Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors

arXiv:2403.11407v1 Announce Type: cross
Abstract: Interest in the use of Denoising Diffusion Models (DDM) as priors for solving inverse Bayesian problems has recently increased significantly. However, sampling from the resulting posterior distribution poses a challenge. To solve this problem, previous works have proposed approximations to bias the drift term of the diffusion. In this work, we take a different approach and utilize the specific structure of the DDM prior to define a set of intermediate and simpler posterior sampling problems, …

abstract arxiv bayesian bias challenge cs.lg denoising diffusion diffusion models distribution drift eess.iv however posterior sampling solve stat.ml type