A stochastic approximation procedure in the case of weakly dependent observations
Teoriâ veroâtnostej i ee primeneniâ, Tome 24 (1979) no. 1, pp. 34-51
Cet article a éte moissonné depuis la source Math-Net.Ru
The Robbins–Monro process is discussed. It is assumed that the observations, statistically dependent, satisfy Kolmogorov's mixing condition (1.7) or, for a special process $G$ (see condition (1.5)), Rosenblatt's mixing condition (1.6). The convergence of the Robbins–Monro process, its asymptotic normality and the convergence of moments are investigated.
@article{TVP_1979_24_1_a2,
author = {A. N. Borodin},
title = {A stochastic approximation procedure in the case of weakly dependent observations},
journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
pages = {34--51},
year = {1979},
volume = {24},
number = {1},
language = {ru},
url = {http://geodesic.mathdoc.fr/item/TVP_1979_24_1_a2/}
}
A. N. Borodin. A stochastic approximation procedure in the case of weakly dependent observations. Teoriâ veroâtnostej i ee primeneniâ, Tome 24 (1979) no. 1, pp. 34-51. http://geodesic.mathdoc.fr/item/TVP_1979_24_1_a2/