AI RESEARCH
Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraints
arXiv CS.LG
•
ArXi:2601.21033v2 Announce Type: replace Diffusion models cannot enforce hard constraints, yet applications in the physical sciences demand exact satisfaction of conservation laws, boundary conditions, and observational consistency. In this work, we identify a corrector kernel whose unique stationary distribution is the constrained marginal at each noise level, and approximate it by iteratively projecting through the denoiser and renoising via the forward kernel. The resulting Predict-Project-Renoise (PPR) algorithm enables sampling from pretrained diffusion models under hard constraints.