Picard Proximal Monte Carlo for Parallel Bayesian Imaging with Score-Based Generative Priors

arXiv:2608.17666v1 Announce Type: new Abstract: Bayesian imaging inverse problems often require sampling from high-dimensional posterior distributions. While recent score-based and diffusion models provide expressive Bayesian priors, their sampling procedures remain inherently sequential and computationally expensive for large-scale imaging applications. We propose PiX-MC, a time-parallel posterior sampling framework based on proximal Langevin dynamics and Picard iteration. The proximal-likelihood formulation exploits the fact that many imaging likelihoods admit efficient, problem-specific proximal operators, while Picard refinement exposes parallelism across discretization nodes and naturally supports multi-GPU implementation. To further improve practical scalability and sampling performance, we develop multi-block and annealed variants of the proposed framework. We establish convergence guarantees under transparent assumptions, accommodating non-log-concave posteriors, imperfect learned score models, multi-block implementations, and annealing schedules. Experiments on a diverse collection of imaging inverse problems demonstrate that PiX-MC substantially reduces wall-clock time while preserving reconstruction quality. On a 512imes512imes80 sparse-view computed tomography (CT) problem, annealed multi-block PiX-MC achieves up to a 50imes runtime speedup over the standard Langevin sampler using eight GPUs.

Related

• Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling
• Outlier-robust Diffusion Posterior Sampling for Bayesian Inverse Problems
• Leveraging generative models to assist Monte Carlo sampling
• Proximal-Based Generative Modeling for Bayesian Inverse Problems

Source: arXiv cs.LG | 2026-08-19