Generalized alternating direction method of multipliers: new theoretical insights and applications

DOI10.1007/s12532-015-0078-2zbMath1353.90110OpenAlexW2003423725WikidataQ87879565 ScholiaQ87879565MaRDI QIDQ2516351

Ethan X. Fang, Han Liu, Bing-sheng He, Xiao-Ming Yuan

Publication date: 31 July 2015

Published in: Mathematical Programming Computation (Search for Journal in Brave)

Full work available at URL: http://europepmc.org/articles/pmc5394583

zbMATH Keywords

convergence ratesalternating direction methodstatistical learningseparable convex optimizationmodification

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Convex programming (90C25) Large-scale problems in mathematical programming (90C06)

Related Items

A rank-two relaxed parallel splitting version of the augmented Lagrangian method with step size in (0,2) for separable convex programming, The symmetric ADMM with indefinite proximal regularization and its application, Matrix completion via max-norm constrained optimization, Partial Error Bound Conditions and the Linear Convergence Rate of the Alternating Direction Method of Multipliers, An inertial Bregman generalized alternating direction method of multipliers for nonconvex optimization, Iteration-complexity analysis of a generalized alternating direction method of multipliers, Convergence Study on the Symmetric Version of ADMM with Larger Step Sizes, Unnamed Item, A proximal point analysis of the preconditioned alternating direction method of multipliers, Some extensions of the operator splitting schemes based on Lagrangian and primal–dual: a unified proximal point analysis, Covariance structure estimation with Laplace approximation, An inexact proximal generalized alternating direction method of multipliers, Image segmentation based on the hybrid bias field correction, Complexity analysis of a stochastic variant of generalized alternating direction method of multipliers, Linearized generalized ADMM-based algorithm for multi-block linearly constrained separable convex programming in real-world applications, A generalized forward-backward splitting operator: degenerate analysis and applications, Accelerated stochastic Peaceman-Rachford method for empirical risk minimization, A new stopping criterion for Eckstein and Bertsekas's generalized alternating direction method of multipliers, Low Rank and Total Variation Based Two-Phase Method for Image Deblurring with Salt-and-Pepper Impulse Noise, Projection Test for Mean Vector in High Dimensions, A unified and tight linear convergence analysis of the relaxed proximal point algorithm, Improved Pointwise Iteration-Complexity of A Regularized ADMM and of a Regularized Non-Euclidean HPE Framework, Symmetric alternating direction method with indefinite proximal regularization for linearly constrained convex optimization, Preconditioned ADMM for a class of bilinear programming problems, On the optimal linear convergence rate of a generalized proximal point algorithm, The alternating direction method of multipliers for finding the distance between ellipsoids, Max-norm optimization for robust matrix recovery, A computation study on an integrated alternating direction method of multipliers for large scale optimization, A symmetric version of the generalized alternating direction method of multipliers for two-block separable convex programming, Learning latent variable Gaussian graphical model for biomolecular network with low sample complexity, Analysis of fully preconditioned alternating direction method of multipliers with relaxation in Hilbert spaces, The generalized proximal point algorithm with step size 2 is not necessarily convergent, Pointwise and ergodic convergence rates of a variable metric proximal alternating direction method of multipliers, Preconditioned Douglas-Rachford type primal-dual method for solving composite monotone inclusion problems with applications, On the iteration-complexity of a non-Euclidean hybrid proximal extragradient framework and of a proximal ADMM, GADMM, A partially inexact proximal alternating direction method of multipliers and its iteration-complexity analysis, An efficient Peaceman–Rachford splitting method for constrained TGV-shearlet-based MRI reconstruction, Dimension reduction for block-missing data based on sparse sliced inverse regression, Generalized ADMM with optimal indefinite proximal term for linearly constrained convex optimization, An inexact symmetric ADMM algorithm with indefinite proximal term for sparse signal recovery and image restoration problems, On the pointwise iteration-complexity of a dynamic regularized ADMM with over-relaxation stepsize

Uses Software

• Matlab
• penalizedLDA
• fRMA

Cites Work

• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
• Nearly unbiased variable selection under minimax concave penalty
• The Adaptive Lasso and Its Oracle Properties
• Sparse linear discriminant analysis by thresholding for high dimensional data
• The solution path of the generalized lasso
• A unified primal-dual algorithm framework based on Bregman iteration
• On the convergence rate of Douglas-Rachford operator splitting method
• High-dimensional classification using features annealed independence rules
• 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
• Some convergence properties of a method of multipliers for linearly constrained monotone variational inequalities
• Parallel alternating direction multiplier decomposition of convex programs
• A new inexact alternating directions method for monotone variational inequalities
• Some theory for Fisher's linear discriminant function, `naive Bayes', and some alternatives when there are many more variables than observations
• 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
• A proximal point algorithm revisit on the alternating direction method of multipliers
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• Multiplier and gradient methods
• On the $O(1/n)$ Convergence Rate of the Douglas–Rachford Alternating Direction Method
• Inexact Alternating Direction Methods for Image Recovery
• Penalized Classification using Fisher’s Linear Discriminant
• A Direct Estimation Approach to Sparse Linear Discriminant Analysis
• Frozen robust multiarray analysis (fRMA)
• Bregmanized Nonlocal Regularization for Deconvolution and Sparse Reconstruction
• Splitting Algorithms for the Sum of Two Nonlinear Operators
• Modified Lagrangians in convex programming and their generalizations
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Sparsity and Smoothness Via the Fused Lasso
• The Linearized Alternating Direction Method of Multipliers for Dantzig Selector
• Linearized augmented Lagrangian and alternating direction methods for nuclear norm minimization
• Vast Portfolio Selection With Gross-Exposure Constraints
• On Alternating Direction Methods of Multipliers: A Historical Perspective
• 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
• A Road to Classification in High Dimensional Space: The Regularized Optimal Affine Discriminant
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item