The value function approach to convergence analysis in composite optimization
From MaRDI portal
Abstract: This works aims at understanding further convergence properties of first order local search methods with complex geometries. We focus on the composite optimization model which unifies within a simple formalism many problems of this type. We provide a general convergence analysis of the composite Gauss-Newton method under tameness assumptions (an extension of semi-algebraicity). Tameness is a very general condition satisfied by virtually all problems solved in practice. The analysis is based on recent progresses in understanding convergence properties of sequential convex programming methods through the value function.
Recommendations
- scientific article; zbMATH DE number 1568710
- scientific article; zbMATH DE number 719421
- Convergence of an Inexact Algorithm for Composite Nonsmooth Optimization
- Convergence of an inexact majorization-minimization method for solving a class of composite optimization problems
- Consistent approximations in composite optimization
- Optimality conditions for non-finite valued convex composite functions
- Variational convergence for vector-valued functions and its applications to convex multiobjective optimization
- scientific article; zbMATH DE number 1950396
- Asymptotic analysis in convex composite multiobjective optimization problems
- General convergence analysis of stochastic first-order methods for composite optimization
Cites work
- A Gauss-Newton method for convex composite optimization
- An extended sequential quadratically constrained quadratic programming algorithm for nonlinear, semidefinite, and second-order cone programming
- Clarke Subgradients of Stratifiable Functions
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Convergence of the Iterates of Descent Methods for Analytic Cost Functions
- Descent methods for composite nondifferentiable optimization problems
- Geometric categories and o-minimal structures
- scientific article; zbMATH DE number 3934328 (Why is no real title available?)
- scientific article; zbMATH DE number 1160037 (Why is no real title available?)
- scientific article; zbMATH DE number 3365044 (Why is no real title available?)
- scientific article; zbMATH DE number 3371284 (Why is no real title available?)
- Introductory lectures on convex optimization. A basic course.
- Majorization-minimization procedures and convergence of SQP methods for semi-algebraic and tame programs
- Majorizing Functions and Convergence of the Gauss–Newton Method for Convex Composite Optimization
- On convergence of the Gauss-Newton method for convex composite optimization.
- On gradients of functions definable in o-minimal structures
- On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
- Proximal alternating linearized minimization for nonconvex and nonsmooth problems
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- SNOPT: An SQP Algorithm for Large-Scale Constrained Optimization
- The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
- Variational Analysis
Cited in
(12)- From error bounds to the complexity of first-order descent methods for convex functions
- Proximal methods avoid active strict saddles of weakly convex functions
- Global convergence of model function based Bregman proximal minimization algorithms
- The multiproximal linearization method for convex composite problems
- Efficiency of minimizing compositions of convex functions and smooth maps
- scientific article; zbMATH DE number 5688219 (Why is no real title available?)
- Convergence Rate Analysis of a Sequential Convex Programming Method with Line Search for a Class of Constrained Difference-of-Convex Optimization Problems
- Composite optimization by nonconvex majorization-minimization
- Stochastic proximal linear method for structured non-convex problems
- Convergence Analysis of the Proximal Gradient Method in the Presence of the Kurdyka–Łojasiewicz Property Without Global Lipschitz Assumptions
- Efficiency of higher-order algorithms for minimizing composite functions
- A systematic approach to general higher-order majorization-minimization algorithms for (non)convex optimization
This page was built for publication: The value function approach to convergence analysis in composite optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1709968)
