Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems

• URL: http://arxiv.org/abs/2606.22346v1
• Date: Sun, 21 Jun 2026 05:47:26 GMT
• Title: Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems
• Abstract summary: We introduce Annealing Posterior Sampling (FAPS), to our knowledge the first function-space posterior sampling framework that unifies process regression and PDE inverse problems.<n>FAPS is built on pretrained function-space flow-matching priors, supports variable query discretizations, and avoids explicit prior-density evaluation.
• Score: 24.863179232277798
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Principled regression for stochastic processes is a long-standing challenge with deep connections to scientific inverse problems. We introduce Flow Annealing Posterior Sampling (FAPS), to our knowledge the first function-space posterior sampling framework that unifies stochastic-process regression and PDE inverse problems. Built on pretrained function-space flow-matching priors, FAPS enables likelihood-guided posterior inference from sparse and noisy observations, supports variable query discretizations, and avoids explicit prior-density evaluation. Its Langevin correction uses a low-rank covariance preconditioner to exploit dominant function-space correlations across discretizations. Across Gaussian and non-Gaussian stochastic-process regression benchmarks and diverse PDE inverse problems, FAPS produces coherent posterior samples with accurate uncertainty quantification, significantly outperforming existing functional regression baselines and achieving competitive or better PDE noisy inverse performance than diffusion-based posterior samplers while reducing test-time sampling cost.

Related papers

• Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems [16.685352002333225]
  Posterior sampling with a pretrained diffusion prior is governed by a conditional score whose likelihood component is generally intractable.<n>We show that a noise-conditioned path whose targets approach the clean posterior produces a continuous surrogate SDE.<n>Experiments on FFHQ and ImageNet with 100 score evaluations demonstrate competitive reconstruction fidelity for superresolution and deblurring.
  arXiv  Detail & Related papers  (2026-08-15T09:38:41Z)
• Latent Diffusion Posterior Sampling with Surrogate Likelihood Guidance for PDE Inverse Problems [48.15157016272698]
  latent-space diffusion posterior sampling (L-DPS) is an approximate Bayesian framework for high-dimensional inverse problems governed by partial differential equations (PDEs)<n>L-DPS produces accurate and robust inverse solutions, reduces inference cost relative to full-space DPS, and outperforms amortized inverse baselines in sparse and noisy regimes.
  arXiv  Detail & Related papers  (2026-06-25T04:33:44Z)
• A Stabilized Path-Space Approach to Diffusion-Based Posterior Sampling [12.537644240443086]
  Diffusion models provide expressive data-driven priors for inverse problems.<n>Many diffusion posterior samplers rely on guidance approximations that can fail for nonlinear operators and multimodal posteriors.<n>We develop a stabilized path-space framework for diffusion-based posterior sampling.
  arXiv  Detail & Related papers  (2026-06-10T21:55:55Z)
• Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models [56.67321805551389]
  Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators.<n>The sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy.<n>We propose a new sampler that balances effective exploration with stability.
  arXiv  Detail & Related papers  (2026-05-22T11:37:22Z)
• Consistency Regularised Gradient Flows for Inverse Problems [0.9974630621313313]
  Vision-Language Latent Diffusion Models (LDMs) provide powerful generative priors for inverse problems.<n>Existing LDM-based inverse solvers require a large number of neural function evaluations (NFEs) and backpropagation through large pretrained components.<n>We propose a unified Euclidean-Wasserstein-2 gradient-flow framework that jointly performs posterior sampling and prompt optimization in the latent space.
  arXiv  Detail & Related papers  (2026-05-08T15:45:34Z)
• Supervised Guidance Training for Infinite-Dimensional Diffusion Models [47.65586147952857]
  In inverse problems, the aim is to sample from a posterior distribution over functions obtained by conditioning a prior.<n>We prove that the models can be conditioned using an infinite-dimensional extension of Doob's $h$-transform.<n>We propose a simulation-free score matching objective (called Supervised Guidance Training) enabling efficient and stable posterior sampling.
  arXiv  Detail & Related papers  (2026-01-28T16:39:39Z)
• Solving Diffusion Inverse Problems with Restart Posterior Sampling [2.9527010146189556]
  Inverse problems are fundamental to science and engineering, where the goal is to infer an underlying signal or state from noisy measurements.<n>Recent approaches employ diffusion models as powerful implicit priors for such problems, owing to their ability to capture complex data distributions.<n>We propose Restart for Posterior Sampling (RePS), a general and efficient framework for solving both linear and non-linear inverse problems.
  arXiv  Detail & Related papers  (2025-11-24T20:42:33Z)
• DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing [5.215481191227242]
  We introduce textbfDAPS++, which allows the likelihood term to guide inference more directly while maintaining numerical stability.<n>textbfDAPS++ achieves high computational efficiency and robust reconstruction performance across diverse image restoration tasks.
  arXiv  Detail & Related papers  (2025-11-21T08:28:36Z)
• Amortized Posterior Sampling with Diffusion Prior Distillation [55.03585818289934]
  Amortized Posterior Sampling is a novel variational inference approach for efficient posterior sampling in inverse problems.<n>Our method trains a conditional flow model to minimize the divergence between the variational distribution and the posterior distribution implicitly defined by the diffusion model.<n>Unlike existing methods, our approach is unsupervised, requires no paired training data, and is applicable to both Euclidean and non-Euclidean domains.
  arXiv  Detail & Related papers  (2024-07-25T09:53:12Z)
• Taming Score-Based Diffusion Priors for Infinite-Dimensional Nonlinear Inverse Problems [4.42498215122234]
  This work introduces a sampling method capable of solving Bayesian inverse problems in function space. It does not assume the log-concavity of the likelihood, meaning that it is compatible with nonlinear inverse problems. A novel convergence analysis is conducted, inspired by the fixed-point methods established for traditional regularization-by-denoising algorithms.
  arXiv  Detail & Related papers  (2024-05-24T16:17:01Z)
• Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance [52.093434664236014]
  Recent diffusion models provide a promising zero-shot solution to noisy linear inverse problems without retraining for specific inverse problems. Inspired by this finding, we propose to improve recent methods by using more principled covariance determined by maximum likelihood estimation.
  arXiv  Detail & Related papers  (2024-02-03T13:35:39Z)
• Diffusion Posterior Sampling for General Noisy Inverse Problems [50.873313752797124]
  We extend diffusion solvers to handle noisy (non)linear inverse problems via approximation of the posterior sampling. Our method demonstrates that diffusion models can incorporate various measurement noise statistics.
  arXiv  Detail & Related papers  (2022-09-29T11:12:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.