Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework

• URL: http://arxiv.org/abs/2603.10281v1
• Date: Tue, 10 Mar 2026 23:55:00 GMT
• Title: Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework
• Abstract summary: We develop ADMM plug-and-play (ADMM) that embeds a three-stage denoiser into ADMM.<n>Experiments on a range inverse problems demonstrate that our method consistently improves quality over a variety baselines solution.
• Score: 8.895254408079316
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While score-based generative models have emerged as powerful priors for solving inverse problems, directly integrating them into optimization algorithms such as ADMM remains nontrivial. Two central challenges arise: i) the mismatch between the noisy data manifolds used to train the score functions and the geometry of ADMM iterates, especially due to the influence of dual variables, and ii) the lack of convergence understanding when ADMM is equipped with score-based denoisers. To address the manifold mismatch issue, we propose ADMM plug-and-play (ADMM-PnP) with the AC-DC denoiser, a new framework that embeds a three-stage denoiser into ADMM: (1) auto-correction (AC) via additive Gaussian noise, (2) directional correction (DC) using conditional Langevin dynamics, and (3) score-based denoising. In terms of convergence, we establish two results: first, under proper denoiser parameters, each ADMM iteration is a weakly nonexpansive operator, ensuring high-probability fixed-point $\textit{ball convergence}$ using a constant step size; second, under more relaxed conditions, the AC-DC denoiser is a bounded denoiser, which leads to convergence under an adaptive step size schedule. Experiments on a range of inverse problems demonstrate that our method consistently improves solution quality over a variety of baselines.

Related papers

• Test-time Adaptive Hierarchical Co-enhanced Denoising Network for Reliable Multimodal Classification [55.56234913868664]
  We propose Test-time Adaptive Hierarchical Co-enhanced Denoising Network (TAHCD) for reliable learning on multimodal data.<n>The proposed method achieves superior classification performance, robustness, and generalization compared with state-of-the-art reliable multimodal learning approaches.
  arXiv  Detail & Related papers  (2026-01-12T03:14:12Z)
• CoCoA Is ADMM: Unifying Two Paradigms in Distributed Optimization [6.743429869405684]
  We consider primal-dual algorithms for general empirical risk minimization problems in distributed settings.<n>We show that both classes of algorithms can be transformed into a unified update form that involves only primal and dual variables.
  arXiv  Detail & Related papers  (2025-02-01T15:56:11Z)
• Decoupling Training-Free Guided Diffusion by ADMM [17.425995507142467]
  We propose a novel framework that distinctly decouples the unconditional generation model and the guided loss function. We develop a new algorithm based on the Alternating Direction Method of Multipliers (ADMM) to adaptively balance these components. Our experiments demonstrate that our proposed method ADMMDiff consistently generates high-quality samples.
  arXiv  Detail & Related papers  (2024-11-18T23:05:54Z)
• Meta-Learning Adversarial Bandit Algorithms [55.72892209124227]
  We study online meta-learning with bandit feedback. We learn to tune online mirror descent generalization (OMD) with self-concordant barrier regularizers.
  arXiv  Detail & Related papers  (2023-07-05T13:52:10Z)
• Overlap-guided Gaussian Mixture Models for Point Cloud Registration [61.250516170418784]
  Probabilistic 3D point cloud registration methods have shown competitive performance in overcoming noise, outliers, and density variations. This paper proposes a novel overlap-guided probabilistic registration approach that computes the optimal transformation from matched Gaussian Mixture Model (GMM) parameters.
  arXiv  Detail & Related papers  (2022-10-17T08:02:33Z)
• A Distributed Algorithm for Measure-valued Optimization with Additive Objective [1.0965065178451106]
  We propose a distributed nonvalued algorithm for solving measure-parametric optimization problems with additive objectives. The proposed algorithm comprises a two-layer alternating direction multipliers (ADMM) The overall algorithm realizes operator splitting gradient for flows in the manifold of probability measures.
  arXiv  Detail & Related papers  (2022-02-17T23:09:41Z)
• A Convergent ADMM Framework for Efficient Neural Network Training [17.764095204676973]
  Alternating Direction Method of Multipliers (ADMM) has achieved tremendous success in many classification and regression applications. We propose a novel framework to solve a general neural network training problem via ADMM (dlADMM) to address these challenges simultaneously. Experiments on seven benchmark datasets demonstrate the convergence, efficiency, and effectiveness of our proposed dlADMM algorithm.
  arXiv  Detail & Related papers  (2021-12-22T01:55:24Z)
• Preconditioned Plug-and-Play ADMM with Locally Adjustable Denoiser for Image Restoration [54.23646128082018]
  We extend the concept of plug-and-play optimization to use denoisers that can be parameterized for non-constant noise variance. We show that our pixel-wise adjustable denoiser, along with a suitable preconditioning strategy, can further improve the plug-and-play ADMM approach for several applications.
  arXiv  Detail & Related papers  (2021-10-01T15:46:35Z)
• A Framework of Inertial Alternating Direction Method of Multipliers for Non-Convex Non-Smooth Optimization [17.553531291690025]
  We propose an algorithmic framework dubbed alternating methods of multipliers (iADMM) for solving a class of non nonsmooth multiblock composite problems. Our framework employs the general-major surrogateization (MM) principle to update each block of variables to unify the convergence analysis of previous ADMM schemes.
  arXiv  Detail & Related papers  (2021-02-10T13:55:28Z)
• ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning [91.13797346047984]
  We introduce ADAHESSIAN, a second order optimization algorithm which dynamically incorporates the curvature of the loss function via ADAptive estimates. We show that ADAHESSIAN achieves new state-of-the-art results by a large margin as compared to other adaptive optimization methods.
  arXiv  Detail & Related papers  (2020-06-01T05:00:51Z)
• Compositional ADAM: An Adaptive Compositional Solver [69.31447856853833]
  C-ADAM is the first adaptive solver for compositional problems involving a non-linear functional nesting of expected values. We prove that C-ADAM converges to a stationary point in $mathcalO(delta-2.25)$ with $delta$ being a precision parameter.
  arXiv  Detail & Related papers  (2020-02-10T14:00:45Z)

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.