Iteration-complexity analysis of a generalized alternating direction method of multipliers

DOI10.1007/s10898-018-0697-zzbMath1482.90143arXiv1705.06191MaRDI QIDQ2633539

V. A. Adona, Jefferson G. Melo, Max L. N. Gonçalves

Publication date: 9 May 2019

Published in: Journal of Global Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1705.06191

zbMATH Keywords

convex program; hybrid extragradient method; generalized alternating direction method of multipliers; ergodic iteration-complexity; pointwise iteration-complexity

Mathematics Subject Classification ID

90C25: Convex programming

90C60: Abstract computational complexity for mathematical programming problems

65K10: Numerical optimization and variational techniques

47H05: Monotone operators and generalizations

49M27: Decomposition methods

Related Items

A partially inexact ADMM with o(1/n) asymptotic convergence rate, 𝒪(1/n) complexity, and immediate relative error tolerance, An inexact ADMM with proximal-indefinite term and larger stepsize, An inertial Bregman generalized alternating direction method of multipliers for nonconvex optimization, An inexact proximal generalized alternating direction method of multipliers, A partially inexact proximal alternating direction method of multipliers and its iteration-complexity analysis

Uses Software

• GADMM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
• On the convergence properties of a majorized alternating direction method of multipliers for linearly constrained convex optimization problems with coupled objective functions
• An extragradient-based alternating direction method for convex minimization
• A symmetric version of the generalized alternating direction method of multipliers for two-block separable convex programming
• Pointwise and ergodic convergence rates of a variable metric proximal alternating direction method of multipliers
• On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators
• A dual algorithm for the solution of nonlinear variational problems via finite element approximation
• Parallel alternating direction multiplier decomposition of convex programs
• A hybrid approximate extragradient-proximal point algorithm using the enlargement of a maximal monotone operator
• On the optimal linear convergence rate of a generalized proximal point algorithm
• A first-order primal-dual algorithm for convex problems with applications to imaging
• The Lasso problem and uniqueness
• On non-ergodic convergence rate of Douglas-Rachford alternating direction method of multipliers
• On the global and linear convergence of the generalized alternating direction method of multipliers
• Generalized alternating direction method of multipliers: new theoretical insights and applications
• An $\mathcal O(1/{k})$ Convergence Rate for the Variable Stepsize Bregman Operator Splitting Algorithm
• On the $O(1/n)$ Convergence Rate of the Douglas–Rachford Alternating Direction Method
• Improved Pointwise Iteration-Complexity of A Regularized ADMM and of a Regularized Non-Euclidean HPE Framework
• On the Complexity of the Hybrid Proximal Extragradient Method for the Iterates and the Ergodic Mean
• The Linearized Alternating Direction Method of Multipliers for Dantzig Selector
• Linearized augmented Lagrangian and alternating direction methods for nuclear norm minimization
• A Generalized Proximal Point Algorithm and Its Convergence Rate
• An Accelerated Linearized Alternating Direction Method of Multipliers
• Iteration-Complexity of Block-Decomposition Algorithms and the Alternating Direction Method of Multipliers