Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problems

DOI10.1137/140990309zbMath1356.49061arXiv1410.1390MaRDI QIDQ2954398

Meisam Razaviyayn, Zhi-Quan Luo, Mingyi Hong

Publication date: 13 January 2017

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1410.1390

zbMATH Keywords

nonconvex optimization; consensus; alternating direction method of multipliers; sharing

Mathematics Subject Classification ID

90C26: Nonconvex programming, global optimization

49M37: Numerical methods based on nonlinear programming

93A15: Large-scale systems

Related Items

An Uncertainty-Weighted Asynchronous ADMM Method for Parallel PDE Parameter Estimation, Accelerated Stochastic Algorithms for Nonconvex Finite-Sum and Multiblock Optimization, Alternating Direction Method of Multipliers for a Class of Nonconvex and Nonsmooth Problems with Applications to Background/Foreground Extraction, A nonconvex ADMM for a class of sparse inverse semidefinite quadratic programming problems, Multi-channel Potts-based reconstruction for multi-spectral computed tomography, Complexity and performance of an Augmented Lagrangian algorithm, Limited-Angle CT Reconstruction via the $L_1/L_2$ Minimization, A Global Dual Error Bound and Its Application to the Analysis of Linearly Constrained Nonconvex Optimization, On inexact stochastic splitting methods for a class of nonconvex composite optimization problems with relative error, Unnamed Item, Half-quadratic alternating direction method of multipliers for robust orthogonal tensor approximation, ALADIN‐—An open‐source MATLAB toolbox for distributed non‐convex optimization, A nonlinear kernel SVM Classifier via \(L_{0/1}\) soft-margin loss with classification performance, Distributed Nash equilibrium learning: A second‐order proximal algorithm, Convergence analysis of an improved Bregman-type Peaceman-Rachford splitting algorithm for nonconvex nonseparable linearly constrained optimization problems, Study on \(L_1\) over \(L_2\) Minimization for nonnegative signal recovery, A symmetric splitting sequential quadratic optimization algorithm for two-block nonlinearly constrained nonconvex optimization, A new Lagrangian-based first-order method for nonconvex constrained optimization, Weighted expectile regression with covariates missing at random, Unilateral Orthogonal Nonnegative Matrix Factorization, Training recurrent neural networks by sequential least squares and the alternating direction method of multipliers, Convergence of Bregman Peaceman-Rachford splitting method for nonconvex nonseparable optimization, A Flexible Space-Variant Anisotropic Regularization for Image Restoration with Automated Parameter Selection, Reweighted robust and discriminative latent subspace projection for face recognition, Diffusion optical tomography reconstruction based on convex–nonconvex graph total variation regularization, A structure noise-aware tensor dictionary learning method for high-dimensional data clustering, Synchronous distributed ADMM for consensus convex optimization problems with self-loops, A Symmetric Alternating Direction Method of Multipliers for Separable Nonconvex Minimization Problems, A Semiblind Regularization Algorithm for Inverse Problems with Application to Image Deblurring, Decomposition Methods for Computing Directional Stationary Solutions of a Class of Nonsmooth Nonconvex Optimization Problems, Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity, Total Variation--Based Phase Retrieval for Poisson Noise Removal, Unnamed Item, Unnamed Item, Convergence of alternating direction method for minimizing sum of two nonconvex functions with linear constraints, A randomized incremental primal-dual method for decentralized consensus optimization, On a general smoothly truncated regularization for variational piecewise constant image restoration: construction and convergent algorithms, A stochastic alternating direction method of multipliers for non-smooth and non-convex optimization, Local saddles of relaxed averaged alternating reflections algorithms on phase retrieval, An inertial proximal alternating direction method of multipliers for nonconvex optimization, A General Non-Lipschitz Infimal Convolution Regularized Model: Lower Bound Theory and Algorithm, Unnamed Item, Minimization of $L_1$ Over $L_2$ for Sparse Signal Recovery with Convergence Guarantee, A Splitting Scheme for Flip-Free Distortion Energies, An Alternating Augmented Lagrangian method for constrained nonconvex optimization, The Proximal Alternating Direction Method of Multipliers in the Nonconvex Setting: Convergence Analysis and Rates, A Proximal Alternating Direction Method of Multiplier for Linearly Constrained Nonconvex Minimization, A Scale-Invariant Approach for Sparse Signal Recovery, Douglas--Rachford Splitting and ADMM for Nonconvex Optimization: Tight Convergence Results, ADMM for multiaffine constrained optimization, A Proximal Minimization Algorithm for Structured Nonconvex and Nonsmooth Problems, Blind Ptychographic Phase Retrieval via Convergent Alternating Direction Method of Multipliers, Convergence guarantees for a class of non-convex and non-smooth optimization problems, Alternating direction method of multipliers for penalized zero-variance discriminant analysis, Iteration complexity analysis of multi-block ADMM for a family of convex minimization without strong convexity, Managing randomization in the multi-block alternating direction method of multipliers for quadratic optimization, Weighted hyper-Laplacian prior with overlapping group sparsity for image restoration under Cauchy noise, An alternating direction method of multipliers for MCP-penalized regression with high-dimensional data, A nonconvex formulation for low rank subspace clustering: algorithms and convergence analysis, Global convergence of unmodified 3-block ADMM for a class of convex minimization problems, Low Tucker rank tensor recovery via ADMM based on exact and inexact iteratively reweighted algorithms, Peaceman-Rachford splitting for a class of nonconvex optimization problems, Convergence of ADMM for multi-block nonconvex separable optimization models, A flexible ADMM algorithm for big data applications, Extended ADMM and BCD for nonseparable convex minimization models with quadratic coupling terms: convergence analysis and insights, Distributed adaptive dynamic programming for data-driven optimal control, Learning low-complexity autoregressive models via proximal alternating minimization, Structured nonconvex and nonsmooth optimization: algorithms and iteration complexity analysis, Alternating iterative methods for solving tensor equations with applications, Global convergence of ADMM in nonconvex nonsmooth optimization, Distributed Nash equilibrium seeking under partial-decision information via the alternating direction method of multipliers, A non-smooth and non-convex regularization method for limited-angle CT image reconstruction, Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods, Whiteness constraints in a unified variational framework for image restoration, Distributed optimization and control with ALADIN, Approximate versions of proximal iteratively reweighted algorithms including an extended IP-ICMM for signal and image processing problems, Iterative adaptive nonconvex low-rank tensor approximation to image restoration based on ADMM, Local linear convergence of the alternating direction method of multipliers for nonconvex separable optimization problems, Tractable ADMM schemes for computing KKT points and local minimizers for \(\ell_0\)-minimization problems, Decentralized optimization over tree graphs, Bilinear constraint based ADMM for mixed Poisson-Gaussian noise removal, 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 ADMM-based SQP method for separably smooth nonconvex optimization, An inertial proximal partially symmetric ADMM-based algorithm for linearly constrained multi-block nonconvex optimization problems with applications, A superlinearly convergent splitting feasible sequential quadratic optimization method for two-block large-scale smooth optimization, Convergence and rate analysis of a proximal linearized ADMM for nonconvex nonsmooth optimization, Two-step inertial Bregman alternating minimization algorithm for nonconvex and nonsmooth problems, An adaptive alternating direction method of multipliers, Proximal ADMM for nonconvex and nonsmooth optimization, Efficient low-rank regularization-based algorithms combining advanced techniques for solving tensor completion problems with application to color image recovering, Multiple kernel low-rank representation-based robust multi-view subspace clustering, A survey on some recent developments of alternating direction method of multipliers, Fast and stable nonconvex constrained distributed optimization: the ELLADA algorithm, Douglas-Rachford splitting and ADMM for nonconvex optimization: accelerated and Newton-type linesearch algorithms, An inertial Bregman generalized alternating direction method of multipliers for nonconvex optimization, An alternating minimization method for matrix completion problems, Primal-dual optimization algorithms over Riemannian manifolds: an iteration complexity analysis, Iterative \(p\)-shrinkage thresholding algorithm for low Tucker rank tensor recovery, An overlapping domain decomposition framework without dual formulation for variational imaging problems, How can machine learning and optimization help each other better?, Nonconvex optimization for robust tensor completion from grossly sparse observations, Bregman reweighted alternating minimization and its application to image deblurring, An incremental aggregated proximal ADMM for linearly constrained nonconvex optimization with application to sparse logistic regression problems, Analysis of the alternating direction method of multipliers for nonconvex problems, Multi-block nonconvex nonsmooth proximal ADMM: convergence and rates under Kurdyka-Łojasiewicz property, Local linear convergence of an ADMM-type splitting framework for equality constrained optimization, An efficient non-convex total variation approach for image deblurring and denoising, The alternating direction method of multipliers for finding the distance between ellipsoids, Sparsity reconstruction using nonconvex TGpV-shearlet regularization and constrained projection, Progressive decoupling of linkages in optimization and variational inequalities with elicitable convexity or monotonicity, A new updating method for the damped mass-spring systems, A proximal alternating direction method for multi-block coupled convex optimization, Block-simultaneous direction method of multipliers: a proximal primal-dual splitting algorithm for nonconvex problems with multiple constraints, A hybrid algorithm for the two-trust-region subproblem, Alternating direction method of multipliers for solving dictionary learning models, Alternating direction method of multipliers for nonconvex fused regression problems, A nonconvex model with minimax concave penalty for image restoration, Perturbed proximal primal-dual algorithm for nonconvex nonsmooth optimization, Misspecified nonconvex statistical optimization for sparse phase retrieval, Constrained TV\(_p\)-\(\ell_2\) model for image restoration, Convergence of linear Bregman ADMM for nonconvex and nonsmooth problems with nonseparable structure, Learning doubly stochastic and nearly idempotent affinity matrix for graph-based clustering, On indefinite quadratic optimization over the intersection of balls and linear constraints, A two-level distributed algorithm for nonconvex constrained optimization, A Parallel Douglas–Rachford Algorithm for Minimizing ROF-like Functionals on Images with Values in Symmetric Hadamard Manifolds, Feasibility vs. Optimality in Distributed AC OPF: A Case Study Considering ADMM and ALADIN