Worst-case evaluation complexity for unconstrained nonlinear optimization using high-order regularized models

Ernesto Birgin, John Gardenghi, José-Mario Martinez, Sandra Augusta Santos, Philippe Toint

Résultats de recherche: Papier de travailArticle de travail

10 Téléchargements (Pure)

Résumé

The worst-case evaluation complexity for smooth (possibly nonconvex) unconstrained optimization is considered. It is shown that, if one is willing to use derivatives of the objective function up to order $p$ (for $p\geq 1$) and to assume Lipschitz continuity of the $p$-th derivative, then an $\epsilon$-approximate first-order critical point can be computed in at most $O(\epsilon^{-(p+1)/p})$ evaluations of the problem's objective function and its derivatives. This generalizes and subsumes results known for $p=1$ and $p=2$.
langue originaleAnglais
Lieu de publication2015
ÉditeurNamur center for complex systems
Nombre de pages8
VolumenaXys-05-2015
Etat de la publicationPublié - juin 2015

Série de publications

NomnaXys Technical Reports
EditeurnaXys
Volume05-2015

    Empreinte digitale

Contient cette citation

Birgin, E., Gardenghi, J., Martinez, J-M., Santos, S. A., & Toint, P. (2015). Worst-case evaluation complexity for unconstrained nonlinear optimization using high-order regularized models. (naXys Technical Reports; Vol 05-2015). Namur center for complex systems.