Proximal-Based Generative Modeling for Bayesian Inverse Problems

• URL: http://arxiv.org/abs/2605.13278v1
• Date: Wed, 13 May 2026 09:55:51 GMT
• Title: Proximal-Based Generative Modeling for Bayesian Inverse Problems
• Abstract summary: We propose a novel proximal-based generative modeling (PGM) framework that rigorously circumvents explicit likelihood evaluation.<n>Our framework is built upon a theoretical equivalence between Gaussian convolution in diffusion processes and Moreau-Yosida regularization in nonsmooth optimization.<n>Experiments demonstrate that PGM significantly surpasses state-of-the-art methods in reconstruction quality and sampling time.
• Score: 38.33757282877801
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Score-based diffusion models demonstrate superior performance in generative tasks but encounter fundamental bottlenecks in inverse problems due to the analytical intractability of the time-dependent likelihood score. To bridge this gap, we propose a novel proximal-based generative modeling (PGM) framework that rigorously circumvents explicit likelihood evaluation. Our framework is built upon a theoretical equivalence between Gaussian convolution in diffusion processes and Moreau-Yosida regularization in nonsmooth optimization. This enables a new sampling mechanism driven by the proposed Moreau score, which admits a closed-form expression via proximal operators. Moreover, we introduce Moreau score matching to learn the proximal operators that rely solely on samples drawn from the prior distribution. Theoretically, PGM eliminates the early-stopping bias inherent in the score-based diffusion model and achieves non-asymptotic convergence. Experiments demonstrate that PGM significantly surpasses state-of-the-art methods in reconstruction quality and sampling time.

Related papers

• Bridging Maximum Likelihood and Optimal Transport for Efficient Inference and Model Selection in Stochastic Block Models [3.8370245746783027]
  We study inference in block models (SBMs) through the lens of optimal transport (OT)<n>We first establish that maximum likelihood variational inference (MLVI) can be interpreted as a semi-relaxed Gromov-Wasserstein (srGW) projection with entropic regularization.<n>We empirically show that such a regularized formulation yields estimators that simultaneously recover model parameters and select the number of parameters in a single optimization problem.
  arXiv  Detail & Related papers  (2026-05-27T13:44:43Z)
• From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models [58.02657021435213]
  We propose a novel Gibbs-based corrector for discrete diffusion models, termed Gibbs-Accelerated Discrete Diffusion (GADD)<n>We show GADD achieves an overall sampling complexity of $mathcalO(mathrmpolylog (varepsilon-1)$, yielding the first such rate for diffusion-based samplers for uniform-rate discrete diffusion models.
  arXiv  Detail & Related papers  (2026-05-26T17:52:28Z)
• InjectFlow: Weak Guides Strong via Orthogonal Injection for Flow Matching [1.974921946982281]
  Flow Matching (FM) has emerged as a leading approach for high-fidelity visual generation.<n>FM models are sensitive to dataset biases, which cause severe semantic degradation when generating out-of-distribution or minority-class samples.<n>We introduce InjectFlow, a novel, training-free method by injecting semantics during the initial velocity field.
  arXiv  Detail & Related papers  (2026-03-19T11:07:14Z)
• Sharp Convergence Rates for Masked Diffusion Models [53.117058231393834]
  We develop a total-variation based analysis for the Euler method that overcomes limitations.<n>Our results relax assumptions on score estimation, improve parameter dependencies, and establish convergence guarantees.<n>Overall, our analysis introduces a direct TV-based error decomposition along the CTMC trajectory and a decoupling-based path-wise analysis for FHS.
  arXiv  Detail & Related papers  (2026-02-26T00:47:51Z)
• Provable Diffusion Posterior Sampling for Bayesian Inversion [13.807494493914335]
  This paper proposes a novel diffusion-based posterior sampling method within a plug-and-play framework.<n>To approximate the posterior score, we develop a Monte Carlo estimator in which particles are generated using Langevin dynamics.<n>On the theoretical side, we provide non-asymptotic error bounds, showing that the method converges even for complex multi-modal target posterior.
  arXiv  Detail & Related papers  (2025-12-08T20:34:05Z)
• Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing [58.52119063742121]
  Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance.<n>This paper addresses the question of how to optimally combine the model's predictions and the provided labels.<n>Our main contribution is the derivation of the Bayes optimal aggregator function to combine the current model's predictions and the given labels.
  arXiv  Detail & Related papers  (2025-05-21T07:16:44Z)
• Benchmarking Diffusion Annealing-Based Bayesian Inverse Problem Solvers [4.429516572803286]
  This work introduces three benchmark problems for evaluating the performance of diffusion model based samplers.<n>The benchmark problems are inspired by problems in image inpainting, x-ray tomography, and phase retrieval.<n>In this setting, approximate ground-truth posterior samples can be obtained, enabling principled evaluation of the performance of posterior sampling algorithms.
  arXiv  Detail & Related papers  (2025-03-04T21:07:15Z)
• Generative Modeling with Bayesian Sample Inference [50.07758840675341]
  We derive a novel generative model from iterative Gaussian posterior inference.<n>Our model uses a sequence of prediction and posterior update steps to iteratively narrow down the unknown sample.<n>In experiments, we demonstrate that our model improves sample quality on ImageNet32 over both BFNs and the closely related Variational Diffusion Models.
  arXiv  Detail & Related papers  (2025-02-11T14:27:10Z)
• Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases [76.9127853906115]
  Bridging the gap between diffusion models and human preferences is crucial for their integration into practical generative. We propose Temporal Diffusion Policy Optimization with critic active neuron Reset (TDPO-R), a policy gradient algorithm that exploits the temporal inductive bias of diffusion models. Empirical results demonstrate the superior efficacy of our methods in mitigating reward overoptimization.
  arXiv  Detail & Related papers  (2024-02-13T15:55:41Z)
• Reverse Diffusion Monte Carlo [19.35592726471155]
  We propose a novel Monte Carlo sampling algorithm called reverse diffusion Monte Carlo (rdMC) rdMC is distinct from the Markov chain Monte Carlo (MCMC) methods.
  arXiv  Detail & Related papers  (2023-07-05T05:42:03Z)
• Loss function based second-order Jensen inequality and its application to particle variational inference [112.58907653042317]
  Particle variational inference (PVI) uses an ensemble of models as an empirical approximation for the posterior distribution. PVI iteratively updates each model with a repulsion force to ensure the diversity of the optimized models. We derive a novel generalization error bound and show that it can be reduced by enhancing the diversity of models.
  arXiv  Detail & Related papers  (2021-06-09T12:13:51Z)
• Approximate Bayesian inference from noisy likelihoods with Gaussian process emulated MCMC [0.24275655667345403]
  We model the log-likelihood function using a Gaussian process (GP) The main methodological innovation is to apply this model to emulate the progression that an exact Metropolis-Hastings (MH) sampler would take. The resulting approximate sampler is conceptually simple and sample-efficient.
  arXiv  Detail & Related papers  (2021-04-08T17:38:02Z)

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.