An algorithm for the minimization of nonsmooth nonconvex functions using inexact evaluations and its worst-case complexity

Résultats de recherche: Contribution à un journal/une revueArticleRevue par des pairs

15 Téléchargements (Pure)

Résumé

An adaptive regularization algorithm using inexact function and derivatives evaluations is proposed for the solution of composite nonsmooth nonconvex optimization. It is shown that this algorithm needs at most O(|log(ϵ)|ϵ-2) evaluations of the problem’s functions and their derivatives for finding an ϵ-approximate first-order stationary point. This complexity bound therefore generalizes that provided by Bellavia et al. (Theoretical study of an adaptive cubic regularization method with dynamic inexact Hessian information. arXiv:1808.06239, 2018) for inexact methods for smooth nonconvex problems, and is within a factor | log (ϵ) | of the optimal bound known for smooth and nonsmooth nonconvex minimization with exact evaluations. A practically more restrictive variant of the algorithm with worst-case complexity O(| log (ϵ) | + ϵ - 2) is also presented.

langue originaleAnglais
Pages (de - à)1-24
Nombre de pages19
journalMathematical Programming
Volume187
Numéro de publication1-2
Les DOIs
Etat de la publicationPublié - 21 janv. 2020

Empreinte digitale Examiner les sujets de recherche de « An algorithm for the minimization of nonsmooth nonconvex functions using inexact evaluations and its worst-case complexity ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation