In this paper we consider a class of stochastic approximation
procedures that arises in linear filtering and regression theory. Our main
result asserts that the stochastic approximation process satisfies an almost
sure invariance principle (with a certain rate of convergence) if the partial
sums of the errors do.
Publié le : 1997-05-14
Classification:
Stochastic approximation,
linear filtering,
almost sure invariance principles,
62L20,
60F17,
62M20
@article{1034625339,
author = {Berger, Erich},
title = {An almost sure invariance principle for stochastic approximation
procedures in linear filtering theory},
journal = {Ann. Appl. Probab.},
volume = {7},
number = {1},
year = {1997},
pages = { 444-459},
language = {en},
url = {http://dml.mathdoc.fr/item/1034625339}
}
Berger, Erich. An almost sure invariance principle for stochastic approximation
procedures in linear filtering theory. Ann. Appl. Probab., Tome 7 (1997) no. 1, pp. 444-459. http://gdmltest.u-ga.fr/item/1034625339/