A Nondeterministic Minimization Algorithm
Author(s)
Caprile, Bruno; Girosi, Federico
DownloadAIM-1254.ps (1.182Mb)
Additional downloads
Metadata
Show full item recordAbstract
The problem of minimizing a multivariate function is recurrent in many disciplines as Physics, Mathematics, Engeneering and, of course, Computer Science. In this paper we describe a simple nondeterministic algorithm which is based on the idea of adaptive noise, and that proved to be particularly effective in the minimization of a class of multivariate, continuous valued, smooth functions, associated with some recent extension of regularization theory by Poggio and Girosi (1990). Results obtained by using this method and a more traditional gradient descent technique are also compared.
Date issued
1990-09-01Other identifiers
AIM-1254
Series/Report no.
AIM-1254