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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zhongqi, Wang, Bingnan, Xiang, Maosheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911848248377344
author Wang, Zhongqi
Wang, Bingnan
Xiang, Maosheng
author_facet Wang, Zhongqi
Wang, Bingnan
Xiang, Maosheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_13866
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Plug-and-Play Algorithm Convergence Analysis From The Standpoint of Stochastic Differential Equation
Wang, Zhongqi
Wang, Bingnan
Xiang, Maosheng
Computer Vision and Pattern Recognition
Probability
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.
title Plug-and-Play Algorithm Convergence Analysis From The Standpoint of Stochastic Differential Equation
topic Computer Vision and Pattern Recognition
Probability
url https://arxiv.org/abs/2404.13866