Globally convergent block-coordinate techniques for unconstrained optimization

DOI10.1080/10556789908805730zbMath0940.65070OpenAlexW2027361795MaRDI QIDQ4254662

Luigi Grippo, Marco Sciandrone

Publication date: 19 July 2000

Published in: Optimization Methods and Software (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/2158/256064

zbMATH Keywords

convergencedecompositionneural networkunconstrained minimizationnonlinear Gauss-Seidel methodinexact line searches

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

An incremental decomposition method for unconstrained optimization, Global optimization issues in deep network regression: an overview, On the convergence of a modified version of SVM^lightalgorithm, Block layer decomposition schemes for training deep neural networks, A globally convergent algorithm for nonconvex optimization based on block coordinate update, Some convergence results on the regularized alternating least-squares method for tensor decomposition, An efficient implementation of the Gauss-Newton method via generalized Krylov subspaces, Serial and parallel approaches for image segmentation by numerical minimization of a second-order functional, Inexact penalty decomposition methods for optimization problems with geometric constraints, Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods, Numerical minimization of a second-order functional for image segmentation, Buffered and reduced multidimensional distribution functions and their application in optimization, Analysis of a variable metric block coordinate method under proximal errors, Low rank matrix completion by alternating steepest descent methods, An automatic \(L_1\)-based regularization method for the analysis of FFC dispersion profiles with quadrupolar peaks, The 2-coordinate descent method for solving double-sided simplex constrained minimization problems, Unifying Abstract Inexact Convergence Theorems and Block Coordinate Variable Metric iPiano, A variable fixing version of the two-block nonlinear constrained Gauss-Seidel algorithm for \(\ell_1\)-regularized least-squares, A cyclic block coordinate descent method with generalized gradient projections, On the convergence of the block nonlinear Gauss-Seidel method under convex constraints, The Analysis of Alternating Minimization Method for Double Sparsity Constrained Optimization Problem, Convergent Decomposition Techniques for Training RBF Neural Networks, GAITA: a Gauss-Seidel iterative thresholding algorithm for \(\ell_q\) regularized least squares regression, A convergent decomposition algorithm for support vector machines, A decomposition algorithm for unconstrained optimization problems with partial derivative information, A non-convex regularization approach for compressive sensing, On the convergence of a Jacobi-type algorithm for singly linearly-constrained problems subject to simple bounds, Rate of convergence analysis of dual-based variables decomposition methods for strongly convex problems, A block coordinate variable metric linesearch based proximal gradient method, Block Coordinate Descent Methods for Semidefinite Programming, A unified convergence framework for nonmonotone inexact decomposition methods, The Supporting Halfspace--Quadratic Programming Strategy for the Dual of the Best Approximation Problem, On the convergence of a block-coordinate incremental gradient method, A variational non-linear constrained model for the inversion of FDEM data*, Network manipulation algorithm based on inexact alternating minimization, On the rate of convergence of alternating minimization for non-smooth non-strongly convex optimization in Banach spaces, On the convergence of inexact block coordinate descent methods for constrained optimization

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Global convergence and stabilization of unconstrained minimization methods without derivatives
• Decomposition algorithm for convex differentiable minimization
• Application of the alternating direction method of multipliers to separable convex programming problems
• Computational methods in optimization. A unified approach.
• A dual algorithm for the solution of nonlinear variational problems via finite element approximation
• Error bounds and convergence analysis of feasible descent methods: A general approach
• On the convergence of the coordinate descent method for convex differentiable minimization
• A proximal-based deomposition method for compositions method for convex minimization problems
• Stopping criteria for linesearch methods without derivatives
• On the Rate of Convergence of a Partially Asynchronous Gradient Projection Algorithm
• Parallel Variable Distribution
• Parallel Gradient Distribution in Unconstrained Optimization
• Partially Asynchronous, Parallel Algorithms for Network Flow and Other Problems
• Note—A Note on the Cyclic Coordinate Ascent Method
• On search directions for minimization algorithms