A stochastic objective-function-free adaptive regularization method with optimal complexity

DOI10.5802/OJMO.41MaRDI QIDQ6961164zbMATH OpenFDO

Authors Serge Gratton, Philippe L. Toint

Publication date 11 July 2025

Published in OJMO. Open Journal of Mathematical Optimization (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.5802/OJMO.41

zbMATH Keywords

adaptive regularization methodsevaluation complexitynonconvex optimizationobjective-function-free-optimization (OFFO)stochastic optimization

Mathematics Subject Classification ID

Stochastic programming (90C15) Nonconvex programming, global optimization (90C26)

Cites work

• A Levenberg-Marquardt method for large nonlinear least-squares problems with dynamic accuracy in functions and gradients
• A note on inexact gradient and Hessian conditions for cubic regularized Newton's method
• A note on solving nonlinear optimization problems in variable precision
• A stochastic line search method with expected complexity analysis
• Adaptive cubic regularisation methods for unconstrained optimization. II: Worst-case function- and derivative-evaluation complexity
• Adaptive cubic regularization methods with dynamic inexact Hessian information and applications to finite-sum minimization
• Adaptive Regularization Algorithms with Inexact Evaluations for Nonconvex Optimization
• Adaptive regularization for nonconvex optimization using inexact function values and randomly perturbed derivatives
• Adaptive regularization minimization algorithms with nonsmooth norms
• Adaptive subgradient methods for online learning and stochastic optimization
• An adaptive trust-region method without function evaluations
• Convergence Properties of an Objective-Function-Free Optimization Regularization Algorithm, Including an \(\boldsymbol{\mathcal{O}(\epsilon^{-3/2})}\) Complexity Bound
• Evaluation complexity of algorithms for nonconvex optimization. Theory, computation and perspectives
• Exact and inexact subsampled Newton methods for optimization
• Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise
• Global convergence rate analysis of unconstrained optimization methods based on probabilistic models
• scientific article; zbMATH DE number 1446863 (Why is no real title available?)
• scientific article; zbMATH DE number 7306906 (Why is no real title available?)
• Inexact tensor methods and their application to stochastic convex optimization
• Lower bounds for finding stationary points I
• On the Lambert \(w\) function
• Optimality Measures for Performance Profiles
• Stochastic analysis of an adaptive cubic regularization method under inexact gradient evaluations and dynamic Hessian accuracy
• Stochastic model-based minimization of weakly convex functions
• Stochastic optimization using a trust-region method and random models
• Stochastic variance-reduced cubic regularization methods
• Sub-sampled Newton methods
• Worst-case evaluation complexity for unconstrained nonlinear optimization using high-order regularized models

Cited in

(1)

• Refining asymptotic complexity bounds for nonconvex optimization methods, including why steepest descent is \(o(\epsilon^{-2})\) rather than \(\mathcal{O}(\epsilon^{-2})\)

This page was built for publication: A stochastic objective-function-free adaptive regularization method with optimal complexity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6961164)