paper-with-me

Papers

Plug-and-Play Algorithm Convergence Analysis From The Standpoint of Stochastic Differential Equation

2024-04-22 · Zhongqi Wang, Bingnan Wang, MaoSheng Xiang

The Plug-and-Play (PnP) algorithm is popular for inverse image problem-solving. However, this algorithm lacks theoretical analysis of its convergence with more advanced plug-in denoisers. We demonstrate that discrete PnP iteration can be described by a continuous stochastic differential equation (SDE). We can also achieve this transformation through Markov process formulation of PnP. Then, we can take a higher standpoint of PnP algorithms from stochastic differential equations, and give a unified framework for the convergence property of PnP according to the solvability condition of its corresponding SDE. We reveal that a much weaker condition, bounded denoiser with Lipschitz continuous measurement function would be enough for its convergence guarantee, instead of previous Lipschitz continuous denoiser condition.

📄 PDF Abstract BibTeX arXiv:2404.13866

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

PnP PnP, or Poll and Pool, is sampling module extension for DETR-type architectures that adaptively allocates its computation…

Similar Papers 제목 키워드 기반

Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applications

2016-05-05 · Stanley H. Chan, Xiran Wang, Omar A. Elgendy

Alternating direction method of multiplier (ADMM) is a widely used algorithm for solving constrained optimization problems in image restoration. Among many useful features, one critical feature of the ADMM algorithm is i…

DenoisingImage DenoisingImage RestorationSuper-Resolution

A New Convergence Analysis of Plug-and-Play Proximal Gradient Descent Under Prior Mismatch

2026-01-14 · Guixian Xu, Jinglai Li, Junqi Tang arxiv

In this work, we provide a new convergence theory for plug-and-play proximal gradient descent (PnP-PGD) under prior mismatch where the denoiser is trained on a different data distribution to the inference task at hand. T…

Convergence Analysis of a Proximal Stochastic Denoising Regularization Algorithm

2024-12-11 · Marien Renaud, Julien Hermant, Nicolas Papadakis

Plug-and-Play methods for image restoration are iterative algorithms that solve a variational problem to recover a clean image from a degraded observation. These algorithms are known to be flexible to changes of degradat…

DenoisingImage Restoration

Gradient Step Denoiser for convergent Plug-and-Play

2021-10-07 · ICLR 2022 4 · Samuel Hurault, Arthur Leclaire, Nicolas Papadakis

Plug-and-Play methods constitute a class of iterative algorithms for imaging problems where regularization is performed by an off-the-shelf denoiser. Although Plug-and-Play methods can lead to tremendous visual performan…

DeblurringSuper-Resolution

Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms

2021-09-25 · Liyuan Zheng, Tanner Fiez, Zane Alumbaugh, Benjamin Chasnov 외

The hierarchical interaction between the actor and critic in actor-critic based reinforcement learning algorithms naturally lends itself to a game-theoretic interpretation. We adopt this viewpoint and model the actor and…

OpenAI Gymreinforcement-learningReinforcement LearningReinforcement Learning (RL)