liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Aspects on Accelerated Convergence in Stochastic Approximation Schemes
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
1994 (English)In: Proceedings of the 33rd IEEE Conference on Decision and Control, 1994, 1649-1652 vol.2 p.Conference paper (Refereed)
Abstract [en]

So called accelerated convergence is an ingenuous idea to improve the asymptotic accuracy in stochastic approximation (gradient based) algorithms. The estimates obtained from the basic algorithm are subjected to a second round of averaging, which leads to optimal accuracy for estimates of time-invariant parameters. In this contribution some simple and approximate calculations are used to get some intuitive insight into these mechanisms. Of particular interest is to investigate the properties of accelerated convergence schemes in tracking situations.

Place, publisher, year, edition, pages
1994. 1649-1652 vol.2 p.
Keyword [en]
Approximation theory, Parameter estimation
National Category
Control Engineering
URN: urn:nbn:se:liu:diva-94129DOI: 10.1109/CDC.1994.411205ISBN: 0-7803-1968-0OAI: diva2:629274
33rd IEEE Conference on Decision and Control, Lake Buena Vista, FL, USA, December, 1994
Available from: 2013-06-16 Created: 2013-06-16 Last updated: 2013-06-16

Open Access in DiVA

No full text

Other links

Publisher's full textRelated report

Search in DiVA

By author/editor
Ljung, Lennart
By organisation
Automatic ControlThe Institute of Technology
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 23 hits
ReferencesLink to record
Permanent link

Direct link