The value function approach to convergence analysis in composite optimization

DOI10.1016/j.orl.2016.10.003zbMath1408.90283arXiv1604.01654OpenAlexW2964204043MaRDI QIDQ1709968

Edouard Pauwels

Publication date: 15 January 2019

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1604.01654

zbMATH Keywords

convergencevalue functionGauss-Newton methodcomposite optimizationKL inequality

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Nonlinear programming (90C30) Methods of quasi-Newton type (90C53)

Related Items

Proximal methods avoid active strict saddles of weakly convex functions ⋮ Global convergence of model function based Bregman proximal minimization algorithms ⋮ From error bounds to the complexity of first-order descent methods for convex functions ⋮ Convergence Analysis of the Proximal Gradient Method in the Presence of the Kurdyka–Łojasiewicz Property Without Global Lipschitz Assumptions ⋮ The multiproximal linearization method for convex composite problems ⋮ Efficiency of higher-order algorithms for minimizing composite functions ⋮ Composite Optimization by Nonconvex Majorization-Minimization ⋮ Efficiency of minimizing compositions of convex functions and smooth maps ⋮ Convergence Rate Analysis of a Sequential Convex Programming Method with Line Search for a Class of Constrained Difference-of-Convex Optimization Problems ⋮ Stochastic proximal linear method for structured non-convex problems

Uses Software

• SNOPT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On local convergence of the method of alternating projections
• Proximal alternating linearized minimization for nonconvex and nonsmooth problems
• On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
• On gradients of functions definable in o-minimal structures
• Introductory lectures on convex optimization. A basic course.
• A Gauss-Newton method for convex composite optimization
• Geometric categories and o-minimal structures
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• An extended sequential quadratically constrained quadratic programming algorithm for nonlinear, semidefinite, and second-order cone programming
• Majorization-Minimization Procedures and Convergence of SQP Methods for Semi-Algebraic and Tame Programs
• Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
• Clarke Subgradients of Stratifiable Functions
• Majorizing Functions and Convergence of the Gauss–Newton Method for Convex Composite Optimization
• Descent methods for composite nondifferentiable optimization problems
• Variational Analysis
• SNOPT: An SQP Algorithm for Large-Scale Constrained Optimization
• The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
• Convergence of the Iterates of Descent Methods for Analytic Cost Functions
• On convergence of the Gauss-Newton method for convex composite optimization.