Deep Block Proximal Linearised Minimisation Algorithm for Non-convex Inverse Problems
Chaoyan Huang, Zhongming Wu, Yanqi Cheng, Tieyong Zeng, Carola-Bibiane, Sch\"onlieb, Angelica I. Aviles-Rivero

TL;DR
This paper introduces a novel inertial block proximal linearised minimisation algorithm for non-convex inverse problems, unifying parallel and alternating update rules, with extensions to deep denoising, demonstrating improved convergence and robustness.
Contribution
The paper proposes a new inertial block proximal linearised minimisation algorithm that unifies existing methods and incorporates deep denoisers, with proven convergence and enhanced performance.
Findings
The algorithms achieve faster convergence in image denoising and deblurring.
The methods demonstrate robustness and improved numerical performance.
Theoretical analysis confirms subsequential and global convergence.
Abstract
Image restoration is typically addressed through non-convex inverse problems, which are often solved using first-order block-wise splitting methods. In this paper, we consider a general type of non-convex optimisation model that captures many inverse image problems and present an inertial block proximal linearised minimisation (iBPLM) algorithm. Our new method unifies the Jacobi-type parallel and the Gauss-Seidel-type alternating update rules, and extends beyond these approaches. The inertial technique is also incorporated into each block-wise subproblem update, which can accelerate numerical convergence. Furthermore, we extend this framework with a plug-and-play variant (PnP-iBPLM) that integrates deep gradient denoisers, offering a flexible and robust solution for complex imaging tasks. We provide comprehensive theoretical analysis, demonstrating both subsequential and global…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSparse and Compressive Sensing Techniques · Optimization and Variational Analysis · Advanced Optimization Algorithms Research
