Provable Diffusion Posterior Sampling for Bayesian Inversion

发布时间：2026-06-08 作者：浏览次数：

Speaker:	焦雨领	DateTime:	2026年6月8日（周一）上午11:00-11:45
Brief Introduction to Speaker: 焦雨领（武汉大学）		Place:	文科楼401
Abstract:This paper proposes a novel diffusion-based posterior sampling method within a plug-and-play (PnP) framework. Our approach constructs a probability transport from an easy-to-sample terminal distribution to the target posterior, using a warm-start strategy to initialize the particles. To approximate the posterior score, we develop a Monte Carlo estimator in which particles are generated using Langevin dynamics, avoiding the heuristic approximations commonly used in prior work. The score governing the Langevin dynamics is learned from data, enabling the model to capture rich structural features of the underlying prior distribution. On the theoretical side, we provide non-asymptotic error bounds, showing that the method converges even for complex, multi-modal target posterior distributions. These bounds explicitly quantify the errors arising from posterior score estimation, the warm-start initialization, and the posterior sampling procedure. Our analysis further clarifies how the prior...