Asymptotic behaviour of a family of gradient algorithms in R^d and Hilbert spaces

Abstract : The asymptotic behaviour of a family of gradient algorithms (including the methods of steepest descent and minimum residues) for the optimisation of bounded quadratic operators in R^d and Hilbert spaces is analyzed. The results obtained generalize those of Akaike (1959) in several directions. First, all algorithms in the family are shown to have the same asymptotic behaviour (convergence to a two-point attractor), which implies in particular that they have similar asymptotic convergence rates. Second, the analysis also covers the Hilbert space case. A detailed analysis of the stability property of the attractor is provided.
Document type :
Journal articles
Liste complète des métadonnées

Cited literature [20 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00259553
Contributor : Luc Pronzato <>
Submitted on : Thursday, February 28, 2008 - 3:04:43 PM
Last modification on : Monday, November 5, 2018 - 3:52:02 PM
Document(s) archivé(s) le : Thursday, May 20, 2010 - 11:44:51 PM

Files

PWZ-Mathprg.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Luc Pronzato, Henry Wynn, Anatoly Zhigljavsky. Asymptotic behaviour of a family of gradient algorithms in R^d and Hilbert spaces. Mathematical Programming, Series A, Springer, 2006, 107, pp.409-438. ⟨10.1007/s10107-005-0602-7⟩. ⟨hal-00259553⟩

Share

Metrics

Record views

414

Files downloads

111