Linearized alternating direction method with parallel splitting and adaptive penalty for separable convex programs in machine learning

DOI10.1007/s10994-014-5469-5zbMath1331.68189arXiv1310.5035MaRDI QIDQ2353007

Zhouchen Lin, Risheng Liu, Hu-An Li

Publication date: 7 July 2015

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1310.5035

zbMATH Keywords

convex programs; alternating direction method; parallel splitting; proximal alternating direction method; adaptive renalty; linearized alternating direction method

Mathematics Subject Classification ID

90C25: Convex programming

90C90: Applications of mathematical programming

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Unnamed Item, A new accelerated positive-indefinite proximal ADMM for constrained separable convex optimization problems, The Proximal Alternating Direction Method of Multipliers in the Nonconvex Setting: Convergence Analysis and Rates, ADMM for multiaffine constrained optimization, An alternate minimization method beyond positive definite proximal regularization: convergence and complexity, Alternating Direction Method of Multipliers for a Class of Nonconvex and Nonsmooth Problems with Applications to Background/Foreground Extraction, Convergence analysis of an improved Bregman-type Peaceman-Rachford splitting algorithm for nonconvex nonseparable linearly constrained optimization problems, An extended linearized alternating direction method of multipliers for fused-Lasso penalized linear regression, The convergence rate of the proximal alternating direction method of multipliers with indefinite proximal regularization, Linearized symmetric multi-block ADMM with indefinite proximal regularization and optimal proximal parameter, Two proximal splitting methods for multi-block separable programming with applications to stable principal component pursuit, Improved proximal ADMM with partially parallel splitting for multi-block separable convex programming, Estimation of the parameters of a weighted nuclear norm model and its application in image denoising, Dual robust regression for pattern classification, Tensorized multi-view subspace representation learning, Tensor Q-rank: new data dependent definition of tensor rank, ADMM-type methods for generalized multi-facility Weber problem, A unified framework for nonconvex nonsmooth sparse and low-rank decomposition by majorization-minimization algorithm, Convergence analysis of positive-indefinite proximal ADMM with a Glowinski's relaxation factor, Weighted nuclear norm minimization and its applications to low level vision, Optimally linearizing the alternating direction method of multipliers for convex programming, Accelerated alternating direction method of multipliers: an optimal \(O(1 / K)\) nonergodic analysis, The symmetric ADMM with indefinite proximal regularization and its application, An accelerated proximal augmented Lagrangian method and its application in compressive sensing, Partial Error Bound Conditions and the Linear Convergence Rate of the Alternating Direction Method of Multipliers

Uses Software

• Yall1

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
• Latent variable graphical model selection via convex optimization
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Fixed point and Bregman iterative methods for matrix rank minimization
• A unified primal-dual algorithm framework based on Bregman iteration
• An alternating direction algorithm for matrix completion with nonnegative factors
• Linearized alternating direction method of multipliers with Gaussian back substitution for separable convex programming
• On the global and linear convergence of the generalized alternating direction method of multipliers
• Exact matrix completion via convex optimization
• On the $O(1/n)$ Convergence Rate of the Douglas–Rachford Alternating Direction Method
• Alternating Direction Method with Gaussian Back Substitution for Separable Convex Programming
• Fast Multiple-Splitting Algorithms for Convex Optimization
• Robust principal component analysis?
• A Singular Value Thresholding Algorithm for Matrix Completion
• The Split Bregman Method for L1-Regularized Problems
• The Group Lasso for Logistic Regression
• Linearized augmented Lagrangian and alternating direction methods for nuclear norm minimization
• Convex Analysis
• The direct extension of ADMM for multi-block convex minimization problems is not necessarily convergent