Exact Evaluation of the Accuracy of Diffusion Models for Inverse Problems with Gaussian Data Distributions

תקציר מקורי באנגליתarXiv:2507.07008v2 Announce Type: replace Abstract: Used as priors for Bayesian inverse problems, diffusion models have recently attracted considerable attention in the literature. Their flexibility and high variance enable them to generate multiple solutions for a given task, such as inpainting, super-resolution, and deblurring. However, there is still a lack of understanding about how accurately these conditional diffusion algorithms perform conditional sampling. In this article, we investigate the errors induced by these models when applied to a Gaussian data distribution for which the score function is exactly known. Within this constrained context, we are able to precisely analyze the discrepancy between the theoretical resolution of inverse problems via conditional sampling and the p