Iteration complexity analysis of multi-block ADMM for a family of convex minimization without strong convexity
From MaRDI portal
Publication:334319
DOI10.1007/S10915-016-0182-0zbMath1348.90522arXiv1504.03087OpenAlexW783438975MaRDI QIDQ334319
Tian-Yi Lin, Shu-Zhong Zhang, Shi-Qian Ma
Publication date: 1 November 2016
Published in: Journal of Scientific Computing (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1504.03087
convex optimizationregularizationconvergence ratealternating direction method of multipliers (ADMM)Kurdyka-Łojasiewicz property
Related Items (22)
Managing randomization in the multi-block alternating direction method of multipliers for quadratic optimization ⋮ Asymmetric forward-backward-adjoint splitting for solving monotone inclusions involving three operators ⋮ Global convergence of unmodified 3-block ADMM for a class of convex minimization problems ⋮ On the sublinear convergence rate of multi-block ADMM ⋮ On unifying multi-view self-representations for clustering by tensor multi-rank minimization ⋮ Primal-Dual First-Order Methods for Affinely Constrained Multi-block Saddle Point Problems ⋮ A two-level distributed algorithm for nonconvex constrained optimization ⋮ First-order algorithms for convex optimization with nonseparable objective and coupled constraints ⋮ Extended ADMM and BCD for nonseparable convex minimization models with quadratic coupling terms: convergence analysis and insights ⋮ Iteration complexity of inexact augmented Lagrangian methods for constrained convex programming ⋮ Structured nonconvex and nonsmooth optimization: algorithms and iteration complexity analysis ⋮ Multi-block nonconvex nonsmooth proximal ADMM: convergence and rates under Kurdyka-Łojasiewicz property ⋮ A generalized alternating direction method of multipliers with semi-proximal terms for convex composite conic programming ⋮ Decomposition into low-rank plus additive matrices for background/foreground separation: a review for a comparative evaluation with a large-scale dataset ⋮ Two Symmetrized Coordinate Descent Methods Can Be $O(n^2)$ Times Slower Than the Randomized Version ⋮ Estimation of Graphical Models through Structured Norm Minimization ⋮ An Efficient Inexact Gauss–Seidel-Based Algorithm for Image Restoration with Mixed Noise ⋮ An extended proximal ADMM algorithm for three-block nonconvex optimization problems ⋮ Multi-block relaxed-dual linear inertial ADMM algorithm for nonconvex and nonsmooth problems with nonseparable structures ⋮ Randomized primal-dual proximal block coordinate updates ⋮ On the Global Linear Convergence of the ADMM with MultiBlock Variables ⋮ On the Convergence Rate of Inexact Majorized sGS ADMM with Indefinite Proximal Terms for Convex Composite Programming
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
- Proximal alternating linearized minimization for nonconvex and nonsmooth problems
- On the sublinear convergence rate of multi-block ADMM
- On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators
- Global convergence of unmodified 3-block ADMM for a class of convex minimization problems
- Parallel multi-block ADMM with \(o(1/k)\) convergence
- A note on the alternating direction method of multipliers
- On the convergence analysis of the alternating direction method of multipliers with three blocks
- 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
- 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
- Recovering Low-Rank and Sparse Components of Matrices from Incomplete and Noisy Observations
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- The Numerical Solution of Parabolic and Elliptic Differential Equations
- On the Numerical Solution of Heat Conduction Problems in Two and Three Space Variables
- A Block Successive Upper-Bound Minimization Method of Multipliers for Linearly Constrained Convex Optimization
- On Full Jacobian Decomposition of the Augmented Lagrangian Method for Separable Convex Programming
- Solving Multiple-Block Separable Convex Minimization Problems Using Two-Block Alternating Direction Method of Multipliers
- Characterizations of Łojasiewicz inequalities: Subgradient flows, talweg, convexity
- Splitting Algorithms for the Sum of Two Nonlinear Operators
- A Convergent 3-Block SemiProximal Alternating Direction Method of Multipliers for Conic Programming with 4-Type Constraints
- Iteration-Complexity of Block-Decomposition Algorithms and the Alternating Direction Method of Multipliers
- Local Linear Convergence of the Alternating Direction Method of Multipliers on Quadratic or Linear Programs
- On the Global Linear Convergence of the ADMM with MultiBlock Variables
- The direct extension of ADMM for multi-block convex minimization problems is not necessarily convergent
This page was built for publication: Iteration complexity analysis of multi-block ADMM for a family of convex minimization without strong convexity
