1. Plug-and-Play Algorithm Convergence Analysis From The Standpoint of Stochastic Differential Equation
- Author
-
Wang, Zhongqi, Wang, Bingnan, and Xiang, Maosheng
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Mathematics - Probability - Abstract
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., Comment: 17pages, Preprint, Under review
- Published
- 2024