Optimization Online


A Generalized Worst-Case Complexity Analysis for Non-Monotone Line Searches

Geovani Grapiglia(grapiglia***at***ufpr.br)
Ekkehard Sachs(sachs***at***uni-trier.de)

Abstract: We study the worst-case complexity of a non-monotone line search framework that covers a wide variety of known techniques published in the literature. In this framework, the non-monotonicity is controlled by a sequence of nonnegative parameters. We obtain complexity bounds to achieve approximate first-order optimality even when this sequence is not summable.

Keywords: Nonlinear optimization, Unconstrained optimization, Non-monotone line search, Worst-case complexity

Category 1: Nonlinear Optimization


Download: [PDF]

Entry Submitted: 11/12/2019
Entry Accepted: 11/12/2019
Entry Last Modified: 11/12/2019

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society