Jump to Content
View Cart
Logged Out Log In
SIAM J. Optim. 16, pp. 531-547 (17 pages)
Convergence of the Iterates of Descent Methods for Analytic Cost Functions
Alerts
Alert Me When Cited
Alert Me When Corrected
Tools
Download Citation
Add to MyScitation
Blog This Article
Print-Friendly
Research Toolkit
Share
Email Abstract
Connotea
CiteULike
del.icio.us
BibSonomy
Tweet this Article
Add to FacebookIn the early eighties Lojasiewicz [in Seminari di Geometria 1982-1983, Università di Bologna, Istituto di Geometria, Dipartimento di Matematica, 1984, pp. 115--117] proved that a bounded solution of a gradient flow for an analytic cost function converges to a well-defined limit point. In this paper, we show that the iterates of numerical descent algorithms, for an analytic cost function, share this convergence property if they satisfy certain natural descent conditions. The results obtained are applicable to a broad class of optimization schemes and strengthen classical "weak convergence" results for descent methods to "strong limit-point convergence" for a large class of cost functions of practical interest. The result does not require that the cost has isolated critical points and requires no assumptions on the convexity of the cost nor any nondegeneracy conditions on the Hessian of the cost at critical points.
© 2005 Society for Industrial and Applied Mathematics
RELATED DATABASES
To view database links for this article,
you need to log in.
KEYWORDS
PUBLICATION DATA
ARTICLE DATA
Permalink
For access to fully linked references, you need to log in.
For access to citing articles, you need to log in.
ALL SIAM Content
Scitation
Google Scholar