2 papers
math.ST2026
Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation
Alois Duston, Tan Bui-Thanh
Sampling from an unnormalized target density by reversing an Ornstein-Uhlenbeck diffusion requires the score of each noise-perturbed marginal law. Two exact identities are availabl…
stat.ML2026
Variance-Reduced Diffusion Sampling via Target Score Identity
Alois Duston, Tan Bui-Thanh
We study variance reduction for score estimation and diffusion-based sampling in settings where the clean (target) score is available or can be approximated. Starting from the Targ…