Worst-case evaluation complexity of regularization methods for smooth unconstrained optimization using Hölder continuous gradients

Résultats de recherche: Contribution à un journal/une revueArticle

3 Téléchargements (Pure)

Résumé

The worst-case behaviour of a general class of regularization algorithms is considered in the case where only objective function values and associated gradient vectors are evaluated. Upper bounds are derived on the number of such evaluations that are needed for the algorithm to produce an approximate first-order critical point whose accuracy is within a user-defined threshold. The analysis covers the entire range of meaningful powers in the regularization term as well as in the Hölder exponent for the gradient. The resulting complexity bounds vary according to the regularization power and the assumed Hölder exponent, recovering known results when available.
langue originaleAnglais
Pages (de - à)1273-1298
Nombre de pages26
journalOptimization Methods and Software
Volume32
Numéro de publication6
Les DOIs
Etat de la publicationPublié - 2 nov. 2017

Empreinte digitale Examiner les sujets de recherche de « Worst-case evaluation complexity of regularization methods for smooth unconstrained optimization using Hölder continuous gradients ». Ensemble, ils forment une empreinte digitale unique.

  • Projets

    Complexity in nonlinear optimization

    TOINT, P., Gould, N. I. M. & Cartis, C.

    1/11/08 → …

    Projet: Recherche

    Activités

    • 2 Discours invité

    A path and some adventures in the jungle of high-order nonlinear optimization

    Philippe Toint (Orateur)

    24 oct. 2017

    Activité: Types de discours ou de présentationDiscours invité

    A path and some adventures in the jungle of high-order nonlinear optimization

    Philippe Toint (Orateur)

    23 oct. 2017

    Activité: Types de discours ou de présentationDiscours invité

    Contient cette citation