Article Dans Une Revue Mathematical Programming, Series A Année : 2020

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

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(ǫ)| ǫ −2) evaluations of the problem's functions and their derivatives for finding an ǫ-approximate first-order stationary point. This complexity bound therefore generalizes that provided by [Bellavia, Gurioli, Morini and Toint, 2018] for inexact methods for smooth nonconvex problems, and is within a factor | log(ǫ)| 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(ǫ)| + ǫ −2) is also presented.

Fichier principal
Vignette du fichier
gratton_26341.pdf (448.53 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-02943960 , version 1 (21-09-2020)

Licence

Identifiants

Citer

Serge Gratton, Ehouarn Simon, Philippe Toint. An algorithm for the minimization of nonsmooth nonconvex functions using inexact evaluations and its worst-case complexity. Mathematical Programming, Series A, 2020, 187, p. 1-24. ⟨10.1007/s10107-020-01466-5⟩. ⟨hal-02943960⟩
288 Consultations
304 Téléchargements

Altmetric

Partager

  • More