Convergence Properties of an Objective-Function-Free Optimization Regularization Algorithm, Including an \(\boldsymbol{\mathcal{O}(\epsilon^{-3/2})}\) Complexity Bound-Reference-Cited by-同舟云学术

Convergence Properties of an Objective-Function-Free Optimization Regularization Algorithm, Including an \(\boldsymbol{\mathcal{O}(\epsilon^{-3/2})}\) Complexity Bound

Published:2023-07-28 Issue:3 Volume:33 Page:1621-1646
ISSN:1052-6234
Container-title:SIAM Journal on Optimization
language:en
Short-container-title:SIAM J. Optim.

Author:

Gratton Serge¹^ORCID,Jerad Sadok²^ORCID,Toint Philippe L.³^ORCID

Affiliation:

1. Université de Toulouse, INP, IRIT, 31013 Toulouse, France.

2. ANITI, Université de Toulouse, INP, IRIT, 31013 Toulouse, France.

3. Namur Center for Complex Systems (naXys), University of Namur, B-5000 Namur, Belgium.

Funder

3IA Artificial and Natural Intelligence Toulouse Institute (ANITI) French “Investing for the FuturePIA3”

Publisher

Society for Industrial & Applied Mathematics (SIAM)

Subject

Theoretical Computer Science,Software,Applied Mathematics

Reference21 articles.

1. Adaptive regularization for nonconvex optimization using inexact function values and randomly perturbed derivatives

2. Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise

3. Worst-case evaluation complexity for unconstrained nonlinear optimization using high-order regularized models

4. Convergence Rate Analysis of a Stochastic Trust-Region Method via Supermartingales

5. Adaptive cubic regularisation methods for unconstrained optimization. Part I: motivation, convergence and numerical results

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Yet another fast variant of Newton’s method for nonconvex optimization;IMA Journal of Numerical Analysis;2024-08-13

2. Complexity of a class of first-order objective-function-free optimization algorithms;Optimization Methods and Software;2024-02-08