A generalized worst-case complexity analysis for non-monotone line searches

Nunes Grapiglia, Geovani;Sachs, E.W.
(2021) Numerical Algorithms — Vol. 87, p. 779-796 (2021)

Files

Grapiglia-Sachs_NUMA_Final.pdf
  • Open Access
  • Adobe PDF
  • 544.75 KB
Download

Details

Authors
Abstract
(en) 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.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Nunes Grapiglia, G., & Sachs, E. W. (2021). A generalized worst-case complexity analysis for non-monotone line searches. Numerical Algorithms, 87, 779-796. https://doi.org/10.1007/s11075-020-00987-6 (Original work published 2021)