A regularization algorithm allowing random noise in derivatives and inexact function values is proposed for computing approximate local critical points of any order for smooth unconstrained optimization problems. For an objective function with Lipschitz continuous p-th derivative and given an arbitrary optimality order q≤p, an upper bound on the number of function and derivatives evaluations is established for this algorithm. This bound is in expectation, and in terms of a power of the required tolerances, this power depending on whether q≤2 or q>2. Moreover these bounds are sharp in the order of the accuracy tolerances. An extension to convexly constrained problems is also outlined.

Adaptive regularization for nonconvex optimization using inexact function values and randomly perturbed derivatives / Bellavia S.; Gurioli G.; Morini B.; Toint P.L.. - In: JOURNAL OF COMPLEXITY. - ISSN 0885-064X. - STAMPA. - 68:(2022), pp. 0-0. [10.1016/j.jco.2021.101591]

Adaptive regularization for nonconvex optimization using inexact function values and randomly perturbed derivatives

Bellavia S.;Gurioli G.;Morini B.;
2022

Abstract

A regularization algorithm allowing random noise in derivatives and inexact function values is proposed for computing approximate local critical points of any order for smooth unconstrained optimization problems. For an objective function with Lipschitz continuous p-th derivative and given an arbitrary optimality order q≤p, an upper bound on the number of function and derivatives evaluations is established for this algorithm. This bound is in expectation, and in terms of a power of the required tolerances, this power depending on whether q≤2 or q>2. Moreover these bounds are sharp in the order of the accuracy tolerances. An extension to convexly constrained problems is also outlined.
2022
68
0
0
Goal 9: Industry, Innovation, and Infrastructure
Bellavia S.; Gurioli G.; Morini B.; Toint P.L.
File in questo prodotto:
File Dimensione Formato  
JCOMP_2021.pdf

Accesso chiuso

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 637.29 kB
Formato Adobe PDF
637.29 kB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1245532
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 9
social impact