A unified analysis of a class of proximal bundle methods for solving hybrid convex composite optimization problems

DOI10.1287/MOOR.2023.1372MaRDI QIDQ6563017zbMATH OpenFDO

Authors Jiaming Liang, Renato D. C. Monteiro

Publication date 27 June 2024

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/MOOR.2023.1372

zbMATH Keywords

hybrid convex composite optimizationiteration-complexityproximal bundle methoduniversal method

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Analysis of algorithms and problem complexity (68Q25) Convex programming (90C25) Nonlinear programming (90C30) Abstract computational complexity for mathematical programming problems (90C60)

Recommendations

• A Proximal Bundle Variant with Optimal Iteration-Complexity for a Large Range of Prox Stepsizes
• A single cut proximal bundle method for stochastic convex composite optimization
• A hybrid bundle method for nonsmooth convex optimization
• A proximal bundle method for a class of nonconvex nonsmooth composite optimization problems
• Convex proximal bundle methods in depth: a unified analysis for inexact oracles

Cited in

(6)

• A Proximal Bundle Variant with Optimal Iteration-Complexity for a Large Range of Prox Stepsizes
• A single cut proximal bundle method for stochastic convex composite optimization
• Universal subgradient and proximal bundle methods for convex and strongly convex hybrid composite optimization
• Proximal oracles for optimization and sampling
• Complexity and numerical experiments of a new adaptive generic proximal bundle method
• A simple uniformly optimal method without line search for convex optimization

This page was built for publication: A unified analysis of a class of proximal bundle methods for solving hybrid convex composite optimization problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6563017)