Linear convergence of epsilon-subgradient descent methods for a class of convex functions

DOI10.1007/S101070050078zbMATH Open1029.90056OpenAlexW1979459040MaRDI QIDQ1806023FDOQ1806023

Publication date: 1 February 2004

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Full work available at URL: http://pure.iiasa.ac.at/id/eprint/4985/1/WP-96-041.pdf

Recommendations

Convergence properties of a conditional $\varepsilon$-subgradient method applied to linear programs
Convergence of some algorithms for convex minimization
A general approach to convergence properties of some methods for nonsmooth convex optimization
Publication:4723574
Convergence rates for deterministic and stochastic subgradient methods without Lipschitz continuity

zbMATH Keywords

convex functions proximal point method resolvent method bundle method linear convergence rate bundle-trust region method epsilon-subgradient descent methods

Mathematics Subject Classification ID

Convex programming (90C25) Nonlinear programming (90C30) Numerical methods based on nonlinear programming (49M37) Nonsmooth analysis (49J52)

Cited In (21)

Nomonotone spectral gradient method for sparse recovery
Linear convergence of the derivative-free proximal bundle method on convex nonsmooth functions, with application to the derivative-free $\mathcal{VU}$-algorithm
On the convergence of conditional $\varepsilon$-subgradient methods for convex programs and convex-concave saddle-point problems.
Randomized smoothing variance reduction method for large-scale non-smooth convex optimization
Subgradient and bundle methods for nonsmooth optimization
Gradient-based method with active set strategy for $\ell _1$ optimization
A Unified Analysis of Descent Sequences in Weakly Convex Optimization, Including Convergence Rates for Bundle Methods
Survey Descent: A Multipoint Generalization of Gradient Descent for Nonsmooth Optimization
Title not available (Why is that?)
Computational efficiency of the simplex embedding method in convex nondifferentiable optimization
New approach to the $\eta $-proximal point algorithm and nonlinear variational inclusion problems
On Rockafellar's theorem using proximal point algorithm involving $H$-maximal monotonicity framework
Comparing different nonsmooth minimization methods and software
Generalized Eckstein-Bertsekas proximal point algorithm involving $(H,\eta )$-monotonicity framework
Super-relaxed $(\eta)$-proximal point algorithms, relaxed $(\eta)$-proximal point algorithms, linear convergence analysis, and nonlinear variational inclusions
Weak convexity and approximate subdifferentials
Generalized Eckstein-Bertsekas proximal point algorithm based ona-maximal monotonicity design
Convergence rates of subgradient methods for quasi-convex optimization problems
Scaling techniques for $\epsilon$-subgradient methods
A coordinate gradient descent method for nonsmooth separable minimization
On the convergence of primal-dual hybrid gradient algorithms for total variation image restoration

This page was built for publication: Linear convergence of epsilon-subgradient descent methods for a class of convex functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1806023)