paper-with-me

홈 › Papers

Optimizing ADMM and Over-Relaxed ADMM Parameters for Linear Quadratic Problems

2024-01-01 · Jintao Song, Wenqi Lu, Yunwen Lei, Yuchao Tang, Zhenkuan Pan, Jinming Duan

The Alternating Direction Method of Multipliers (ADMM) has gained significant attention across a broad spectrum of machine learning applications. Incorporating the over-relaxation technique shows potential for enhancing the convergence rate of ADMM. However, determining optimal algorithmic parameters, including both the associated penalty and relaxation parameters, often relies on empirical approaches tailored to specific problem domains and contextual scenarios. Incorrect parameter selection can significantly hinder ADMM's convergence rate. To address this challenge, in this paper we first propose a general approach to optimize the value of penalty parameter, followed by a novel closed-form formula to compute the optimal relaxation parameter in the context of linear quadratic problems (LQPs). We then experimentally validate our parameter selection methods through random instantiations and diverse imaging applications, encompassing diffeomorphic image registration, image deblurring, and MRI reconstruction.

📄 PDF Abstract BibTeX arXiv:2401.00657

Code (0)

등록된 구현이 없습니다.

Tasks

DeblurringImage DeblurringImage RegistrationMRI Reconstruction

Methods 이 논문이 사용한 방법론

ADMM The alternating direction method of multipliers (ADMM) is an algorithm that solves convex optimization problems by breaking them into smaller pieces, each of which are…

Similar Papers 제목 키워드 기반

Adaptive Relaxed ADMM: Convergence Theory and Practical Implementation

2017-04-10 · CVPR 2017 7 · Zheng Xu, Mario A. T. Figueiredo, Xiaoming Yuan, Christoph Studer 외

Many modern computer vision and machine learning applications rely on solving difficult optimization problems that involve non-differentiable objective functions and constraints. The alternating direction method of multi…

An Explicit Rate Bound for the Over-Relaxed ADMM

2015-12-07 · Guilherme França, José Bento

The framework of Integral Quadratic Constraints of Lessard et al. (2014) reduces the computation of upper bounds on the convergence rate of several optimization algorithms to semi-definite programming (SDP). Followup wor…

Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework

2026-03-10 · Rajesh Shrestha, Xiao Fu arxiv

While score-based generative models have emerged as powerful priors for solving inverse problems, directly integrating them into optimization algorithms such as ADMM remains nontrivial. Two central challenges arise: i) t…

Deep ADMM-Net for Compressive Sensing MRI

2016-12-01 · NeurIPS 2016 12 · Yan Yang, Jian Sun, Huibin Li, Zongben Xu

Compressive Sensing (CS) is an effective approach for fast Magnetic Resonance Imaging (MRI). It aims at reconstructing MR image from a small number of under-sampled data in k-space, and accelerating the data acquisition…

Compressive SensingImage Reconstruction

An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method

2018-05-16 · ICML 2018 7 · Li Shen, Peng Sun, Yitong Wang, Wei Liu 외

We propose a novel algorithmic framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-gradient (VMOR-HPE) method with a global convergence guarantee for the maximal monotone operator inclusion problem. Its itera…