Convergence of ADMM for multi-block nonconvex separable optimization models

DOI10.1007/s11464-017-0631-6zbMath1386.90114OpenAlexW2588594937MaRDI QIDQ1690476

David Z. W. Wang, Deren Han, Ke Guo, Tingting Wu

Publication date: 19 January 2018

Published in: Frontiers of Mathematics in China (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11464-017-0631-6

zbMATH Keywords

nonconvex optimizationseparable structureKurdyka-Lojasiewicz inequalityalternating direction method of multipliers (ADMM)

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Numerical optimization and variational techniques (65K10) Nonsmooth analysis (49J52) Decomposition methods (49M27)

Related Items

An inertial proximal alternating direction method of multipliers for nonconvex optimization, A survey on some recent developments of alternating direction method of multipliers, A combined higher order non-convex total variation with overlapping group sparsity for Poisson noise removal, Convergence of linear Bregman ADMM for nonconvex and nonsmooth problems with nonseparable structure, A Bregman-style partially symmetric alternating direction method of multipliers for nonconvex multi-block optimization, A generalized inertial proximal alternating linearized minimization method for nonconvex nonsmooth problems, Convergence analysis of an ALF-based nonconvex splitting algorithm with SQP structure, A Block Lanczos Method for the Extended Trust-Region Subproblem, Unnamed Item, Local linear convergence of an ADMM-type splitting framework for equality constrained optimization, A proximal fully parallel splitting method for stable principal component pursuit, A symmetric version of the generalized alternating direction method of multipliers for two-block separable convex programming, Relaxed inertial proximal Peaceman-Rachford splitting method for separable convex programming, An extended proximal ADMM algorithm for three-block nonconvex optimization problems, A regularized alternating direction method of multipliers for a class of nonconvex problems, An inertial proximal partially symmetric ADMM-based algorithm for linearly constrained multi-block nonconvex optimization problems with applications

Cites Work

• Unnamed Item
• Unnamed Item
• Proximal alternating linearized minimization for nonconvex and nonsmooth problems
• On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
• A dual algorithm for the solution of nonlinear variational problems via finite element approximation
• On gradients of functions definable in o-minimal structures
• Introductory lectures on convex optimization. A basic course.
• A note on the alternating direction method of multipliers
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• On the convergence of the direct extension of ADMM for three-block separable convex minimization models with one strongly convex function
• Linear Convergence of the Alternating Direction Method of Multipliers for a Class of Convex Optimization Problems
• 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
• A Convergent $3$-Block Semi-Proximal ADMM for Convex Minimization Problems with One Strongly Convex Block
• Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problems
• Alternating direction methods for classical and ptychographic phase retrieval
• Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
• An augmented Lagrangian based parallel splitting method for separable convex minimization with applications to image processing
• Global Convergence of Splitting Methods for Nonconvex Composite Optimization
• Clarke Subgradients of Stratifiable Functions
• Variational Analysis
• Convergence of alternating direction method for minimizing sum of two nonconvex functions with linear constraints
• Convergence Rate Analysis for the Alternating Direction Method of Multipliers with a Substitution Procedure for Separable Convex Programming
• Local Linear Convergence of the Alternating Direction Method of Multipliers for Quadratic Programs
• Local Linear Convergence of the Alternating Direction Method of Multipliers on Quadratic or Linear Programs
• The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
• The direct extension of ADMM for multi-block convex minimization problems is not necessarily convergent