Efficiency of the stochastic approximation method

The practical aspect of the stochastic approximation method (SA) is studied. Specifically, we investigated the efficiency depending on the coefficients that generate the step length in optimization algorithm, as well as the efficiency depending on the type and the level of the corresponding noise...

Full description

Bibliographic Details
Main Author:	Japundžić Miloš
Format:	Article
Language:	English
Published:	University of Belgrade 2012-01-01
Series:	Yugoslav Journal of Operations Research
Subjects:	Stochastic approximation step length efficiency of the stochastic methods noise
Online Access:	http://www.doiserbia.nb.rs/img/doi/0354-0243/2012/0354-02431100003J.pdf

id	doaj-44e573102e6c43ab96fb8f71f1efb7d7
record_format	Article
spelling	doaj-44e573102e6c43ab96fb8f71f1efb7d72020-11-24T23:59:41ZengUniversity of BelgradeYugoslav Journal of Operations Research0354-02431820-743X2012-01-0122113114010.2298/YJOR101124003JEfficiency of the stochastic approximation methodJapundžić MilošThe practical aspect of the stochastic approximation method (SA) is studied. Specifically, we investigated the efficiency depending on the coefficients that generate the step length in optimization algorithm, as well as the efficiency depending on the type and the level of the corresponding noise. Efficiency is measured by the mean values of the objective function at the final estimates of the algorithm, over the specified number of replications. This paper provides suggestions how to choose already mentioned coefficients, in order to achieve better performance of the stochastic approximation algorithm.http://www.doiserbia.nb.rs/img/doi/0354-0243/2012/0354-02431100003J.pdfStochastic approximationstep lengthefficiency of the stochastic methodsnoise
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Japundžić Miloš
spellingShingle	Japundžić Miloš Efficiency of the stochastic approximation method Yugoslav Journal of Operations Research Stochastic approximation step length efficiency of the stochastic methods noise
author_facet	Japundžić Miloš
author_sort	Japundžić Miloš
title	Efficiency of the stochastic approximation method
title_short	Efficiency of the stochastic approximation method
title_full	Efficiency of the stochastic approximation method
title_fullStr	Efficiency of the stochastic approximation method
title_full_unstemmed	Efficiency of the stochastic approximation method
title_sort	efficiency of the stochastic approximation method
publisher	University of Belgrade
series	Yugoslav Journal of Operations Research
issn	0354-0243 1820-743X
publishDate	2012-01-01
description	The practical aspect of the stochastic approximation method (SA) is studied. Specifically, we investigated the efficiency depending on the coefficients that generate the step length in optimization algorithm, as well as the efficiency depending on the type and the level of the corresponding noise. Efficiency is measured by the mean values of the objective function at the final estimates of the algorithm, over the specified number of replications. This paper provides suggestions how to choose already mentioned coefficients, in order to achieve better performance of the stochastic approximation algorithm.
topic	Stochastic approximation step length efficiency of the stochastic methods noise
url	http://www.doiserbia.nb.rs/img/doi/0354-0243/2012/0354-02431100003J.pdf
work_keys_str_mv	AT japundzicmilos efficiencyofthestochasticapproximationmethod
_version_	1725446670822408192

Efficiency of the stochastic approximation method

Similar Items