Accelerated Plug-and-Play Davis-Yin Splitting for Nonconvex Image Reconstruction
Abstract
In this work, we study a class of structured non-convex and non-smooth optimization problems arising in imaging applications, where the objective is the sum of three functions. We consider the Davis-Yin splitting method, a FISTA-type accelerated variant, along with a quasi-Newton line-search method and a plug-and-play (PnP) extension to solve the problem. We develop a unified convergence analysis based on the Davis-Yin envelope under mild assumptions, including the Kurdyka-Łojasiewicz property. Within this framework, we establish subsequential and global convergence of the iterates to stationary points, together with residual convergence rates. We demonstrate the performance of the proposed methods on image restoration and low-rank matrix completion problems. For low-rank matrix completion, we perform experiments on both synthetic data and public datasets to evaluate recovery accuracy and efficiency. In imaging tasks, including image deblurring, we compare the convergence behaviour and reconstruction quality of several algorithmic variants using peak signal-to-noise ratio (PSNR). The results show that FISTA-acceleration and line-search methods improve convergence, while PnP denoisers enhance image quality, and the proposed methods remain competitive on matrix completion tasks.
Related
- Douglas-Rachford splitting method for nonconvex stochastic optimal control
- A restart-free accelerated algorithm for nonconvex minimization: continuous- and discrete-time analysis
- GPU-Accelerated Bregman Douglas-Rachford Splitting for Discrete Optimal Transport
- Regularized coordinate minimization for nonconvex composite optimization with application to quantized image compression
- Accelerated Convergence of a Second-Order Dynamical System and its Application to Splitting Algorithms for Comonotone Inclusions
BibTeX
@misc{roy2026accelerated,
title = {{Accelerated Plug-and-Play Davis-Yin Splitting for Nonconvex Image Reconstruction}},
author = {Kuntal Roy and Pankaj Gautam},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.23840},
eprint = {2609.23840},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.23840},
}
RIS
TY - UNPB
TI - Accelerated Plug-and-Play Davis-Yin Splitting for Nonconvex Image Reconstruction
AU - Kuntal Roy
AU - Pankaj Gautam
PY - 2026
DA - 2026/09/20
PB - arXiv
DO - 10.48550/arxiv.2609.23840
UR - https://arxiv.org/abs/2609.23840
AB - In this work, we study a class of structured non-convex and non-smooth optimization problems arising in imaging applications, where the objective is the sum of three functions. We consider the Davis-Yin splitting method, a FISTA-type accelerated variant, along with a quasi-Newton line-search method and a plug-and-play (PnP) extension to solve the problem. We develop a unified convergence analysis based on the Davis-Yin envelope under mild assumptions, including the Kurdyka-Łojasiewicz property. Within this framework, we establish subsequential and global convergence of the iterates to stationary points, together with residual convergence rates. We demonstrate the performance of the proposed methods on image restoration and low-rank matrix completion problems. For low-rank matrix completion, we perform experiments on both synthetic data and public datasets to evaluate recovery accuracy and efficiency. In imaging tasks, including image deblurring, we compare the convergence behaviour and reconstruction quality of several algorithmic variants using peak signal-to-noise ratio (PSNR). The results show that FISTA-acceleration and line-search methods improve convergence, while PnP denoisers enhance image quality, and the proposed methods remain competitive on matrix completion tasks.
ER -