Almost sure convergence of stochastic gradient processes with matrix step sizes

Jean-Marie Monnez

Statistics & Probability Letters, 2006, vol. 76, issue 5, 531-536

Abstract: We consider a stochastic gradient process, which is a special case of stochastic approximation process, where the positive real step size an is replaced by a random matrix An: Xn+1=Xn-An[backward difference]g(Xn)-AnVn. We give two theorems of almost sure convergence in the case where the equation [backward difference]g=0 has a set of solutions.

Keywords: Stochastic; approximation; Stochastic; gradient (search for similar items in EconPapers)
Date: 2006
References: View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0167-7152(05)00343-3
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:stapro:v:76:y:2006:i:5:p:531-536

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

Access Statistics for this article

Statistics & Probability Letters is currently edited by Somnath Datta and Hira L. Koul

More articles in Statistics & Probability Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().