A Fast Stochastic Plug-and-Play ADMM for Imaging Inverse Problems

• URL: http://arxiv.org/abs/2006.11630v2
• Date: Tue, 23 Jun 2020 08:47:00 GMT
• Title: A Fast Stochastic Plug-and-Play ADMM for Imaging Inverse Problems
• Authors: Junqi Tang, Mike Davies
• Abstract summary: We propose an efficient plug-and-play ( inverse problems) algorithm for imaging applications. Our results demonstrate effectiveness of our approach compared with state-of-the-art methods.
• Score: 5.025654873456756
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work we propose an efficient stochastic plug-and-play (PnP) algorithm for imaging inverse problems. The PnP stochastic gradient descent methods have been recently proposed and shown improved performance in some imaging applications over standard deterministic PnP methods. However, current stochastic PnP methods need to frequently compute the image denoisers which can be computationally expensive. To overcome this limitation, we propose a new stochastic PnP-ADMM method which is based on introducing stochastic gradient descent inner-loops within an inexact ADMM framework. We provide the theoretical guarantee on the fixed-point convergence for our algorithm under standard assumptions. Our numerical results demonstrate the effectiveness of our approach compared with state-of-the-art PnP methods.

Related papers

• PnP-Flow: Plug-and-Play Image Restoration with Flow Matching [2.749898166276854]
  We introduce Plug-and-Play Flow Matching, an algorithm for solving inverse imaging problems. We evaluate its performance on denoising, superresolution, and inpainting tasks.
  arXiv  Detail & Related papers  (2024-10-03T12:13:56Z)
• A Unified Plug-and-Play Algorithm with Projected Landweber Operator for Split Convex Feasibility Problems [6.185478918618347]
  In recent years Plug-and-Play methods have achieved state-resolution-of-the-art performance in inverse imaging problems by replacing operators with denoisers. Applying methods with theoretically guaranteed step sizes is difficult, and algorithms are limited to noise. Project Landweber Operator (PLOPLO) is proposed to address these issues.
  arXiv  Detail & Related papers  (2024-08-22T03:29:51Z)
• Provably Convergent Plug-and-Play Quasi-Newton Methods [5.9974035827998655]
  We propose an efficient method to combine fidelity terms and deep denoisers. We show that the proposed quasi-Newton algorithm is critical points of a weakly convex function. Experiments on imageblurring and super-resolution demonstrate faster convergence as compared to other provable deM methods.
  arXiv  Detail & Related papers  (2023-03-09T20:09:15Z)
• A relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser [6.2484576862659065]
  This paper presents a new convergent Plug-and-fidelity Descent (Play) algorithm. The algorithm converges for a wider range of regular convexization parameters, thus allowing more accurate restoration of an image.
  arXiv  Detail & Related papers  (2023-01-31T16:11:47Z)
• Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration [63.15453821022452]
  Recent developments in approaches based on deep learning have achieved sub-second runtimes for DiffIR. We propose a simple iterative scheme that functionally composes intermediate non-stationary velocity fields. We then propose a convex optimisation model that uses a regularisation term of arbitrary order to impose smoothness on these velocity fields.
  arXiv  Detail & Related papers  (2021-09-26T19:56:45Z)
• Parallel Stochastic Mirror Descent for MDPs [72.75921150912556]
  We consider the problem of learning the optimal policy for infinite-horizon Markov decision processes (MDPs) Some variant of Mirror Descent is proposed for convex programming problems with Lipschitz-continuous functionals. We analyze this algorithm in a general case and obtain an estimate of the convergence rate that does not accumulate errors during the operation of the method.
  arXiv  Detail & Related papers  (2021-02-27T19:28:39Z)
• TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems [22.239477171296056]
  Plug-and-Play (MM) is a non- optimization framework that combines numerical algorithms, for example, with advanced denoising priors. We discuss several practical considerations of more denoisers, which together with our learned strategies are state-of-the-art results.
  arXiv  Detail & Related papers  (2020-11-18T14:19:30Z)
• Logistic Q-Learning [87.00813469969167]
  We propose a new reinforcement learning algorithm derived from a regularized linear-programming formulation of optimal control in MDPs. The main feature of our algorithm is a convex loss function for policy evaluation that serves as a theoretically sound alternative to the widely used squared Bellman error.
  arXiv  Detail & Related papers  (2020-10-21T17:14:31Z)
• Gaussian MRF Covariance Modeling for Efficient Black-Box Adversarial Attacks [86.88061841975482]
  We study the problem of generating adversarial examples in a black-box setting, where we only have access to a zeroth order oracle. We use this setting to find fast one-step adversarial attacks, akin to a black-box version of the Fast Gradient Sign Method(FGSM) We show that the method uses fewer queries and achieves higher attack success rates than the current state of the art.
  arXiv  Detail & Related papers  (2020-10-08T18:36:51Z)
• Momentum-Based Policy Gradient Methods [133.53164856723782]
  We propose a class of efficient momentum-based policy gradient methods for the model-free reinforcement learning. In particular, we present a non-adaptive version of IS-MBPG method, which also reaches the best known sample complexity of $O(epsilon-3)$ without any large batches.
  arXiv  Detail & Related papers  (2020-07-13T20:44:15Z)
• Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping [69.9674326582747]
  We propose a new accelerated first-order method called clipped-SSTM for smooth convex optimization with heavy-tailed distributed noise in gradients. We prove new complexity that outperform state-of-the-art results in this case. We derive the first non-trivial high-probability complexity bounds for SGD with clipping without light-tails assumption on the noise.
  arXiv  Detail & Related papers  (2020-05-21T17:05:27Z)

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.