A stochastic quasigradient algorithm with variable metric

Uryasev SP (1992). A stochastic quasigradient algorithm with variable metric. Annals of Operations Research 39 (1): 251-267. DOI:10.1007/BF02060944.

Full text not available from this repository.

Abstract

This paper deals with a new variable metric algorithm for stochastic optimization problems. The essence of this is as follows: there exist two stochastic quasigradient algorithms working simultaneously - the first in the main space, the second with respect to the matrices that modify the space variables. Almost sure convergence of the algorithm is proved for the case of the convex (possibly nonsmooth) objective function

Item Type: Article
Research Programs: Decision Analysis and Support (DAS)
Depositing User: Romeo Molina
Date Deposited: 21 Apr 2016 12:03
Last Modified: 21 Apr 2016 12:03
URI: http://pure.iiasa.ac.at/12859

Actions (login required)

View Item View Item

International Institute for Applied Systems Analysis (IIASA)
Schlossplatz 1, A-2361 Laxenburg, Austria
Phone: (+43 2236) 807 0 Fax:(+43 2236) 71 313