CVPRApr 22, 2024

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

arXiv:2404.13866v1h-index: 15
Originality Incremental advance
AI Analysis

This provides a theoretical foundation for convergence in inverse image problems, though it is incremental as it refines existing conditions rather than introducing a new paradigm.

The paper tackles the lack of theoretical convergence analysis for Plug-and-Play algorithms with advanced denoisers by modeling discrete iterations as a continuous stochastic differential equation, revealing that a weaker condition of bounded denoiser with Lipschitz continuous measurement function suffices for convergence instead of the previous Lipschitz continuous denoiser requirement.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes