Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Exact Evaluation of the Accuracy of Diffusion Models for Inverse Problems with Gaussian Data Distributions
Emile Pierret, Bruno Galerne
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…
cs.LG2024
Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors
Emile Pierret, Bruno Galerne
Diffusion or score-based models recently showed high performance in image generation. They rely on a forward and a backward stochastic differential equations (SDE). The sampling of…