Complexity and global rates of trust-region methods based on probabilistic mode - IRIT - Institut de Recherche en Informatique de Toulouse Accéder directement au contenu
Article Dans Une Revue IMA Journal of Numerical Analysis Année : 2018

Complexity and global rates of trust-region methods based on probabilistic mode

Résumé

Trust-region algorithms have been proved to globally converge with probability one when the accuracy of the trust-region models is imposed with a certain probability conditioning on the iteration history. In this paper, we study their complexity, providing global rates and worst case complexity bounds on the number of iterations (with overwhelmingly high probability), for both first and second order measures of optimality. Such results are essentially the same as the ones known for trust-region methods based on deterministic models. The derivation of the global rates and worst case complexity bounds follows closely from a study of direct-search methods based on the companion notion of probabilistic descent.
Fichier principal
Vignette du fichier
gratton_22593.pdf (192.36 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02147973 , version 1 (05-06-2019)

Identifiants

Citer

Serge Gratton, Clément Royer, Luis Vicente, Zaikun Zhang. Complexity and global rates of trust-region methods based on probabilistic mode. IMA Journal of Numerical Analysis, 2018, 38 (3), pp.1579-1597. ⟨10.1093/imanum/drx043⟩. ⟨hal-02147973⟩
31 Consultations
74 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More