🏢 CMAP, Ecole Polytechnique
Divide-and-Conquer Posterior Sampling for Denoising Diffusion priors
·3064 words·15 mins·
loading
·
loading
Machine Learning
Deep Learning
🏢 CMAP, Ecole Polytechnique
Divide-and-Conquer Posterior Sampling (DCPS) efficiently samples complex posterior distributions from denoising diffusion models (DDMs) for Bayesian inverse problems, significantly improving accuracy …