A Line-Search Algorithm Inspired by the Adaptive Cubic Regularization Framework and Complexity Analysis - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Journal of Optimization Theory and Applications Année : 2018

A Line-Search Algorithm Inspired by the Adaptive Cubic Regularization Framework and Complexity Analysis

Résumé

Adaptive regularized framework using cubics has emerged as an alternative to line-search and trust-region algorithms for smooth nonconvex optimization, with an optimal complexity amongst second-order methods. In this paper, we propose and analyze the use of an iteration dependent scaled norm in the adaptive regularized framework using cubics. Within such scaled norm, the obtained method behaves as a line-search algorithm along the quasi- Newton direction with a special backtracking strategy. Under appropriate assumptions, the new algorithm enjoys the same convergence and complexity properties as adaptive regularized algorithm using cubics. The complexity for finding an approximate first-order stationary point can be improved to be optimal whenever a second order version of the proposed algorithm is regarded. In a similar way, using the same scaled norm to define the trust-region neighborhood, we show that the trust-region algorithm behaves as a line-search algorithm. The good potential of the obtained algorithms is shown on a set of large scale optimization problems.
Fichier principal
Vignette du fichier
Bergou_20734.pdf (532.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01872831 , version 1 (12-09-2018)

Identifiants

Citer

El Houcine Bergou, Youssef Diouane, Serge Gratton. A Line-Search Algorithm Inspired by the Adaptive Cubic Regularization Framework and Complexity Analysis. Journal of Optimization Theory and Applications, 2018, 178 (3), pp.885-913. ⟨10.1007/s10957-018-1341-2⟩. ⟨hal-01872831⟩
89 Consultations
36 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More