Geodesic
Martingale models of stochastic approximation and their convergence
Teoriâ veroâtnostej i ee primeneniâ, Tome 44 (1999) no. 2, pp. 278-311 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

Procedures of stochastic approximation are studied from a general theory of stochastic processes point of view. The results on convergence are obtained by the uniform methods both in the case of discrete and of continuous time. The asymptotic analysis (a.s. convergence, asymptotic normality) of procedures is based on the Lyapunov stochastic method, and a study of the rate of convergence of algorithms of stochastic approximation is based on the law of iterated logarithm for martingales.
Keywords: stochastic approximation, martingale methods, stochastic exponents, stochastic Lyapunov method. 
@article{TVP_1999_44_2_a2,
     author = {E. Valkeila and A. V. Melnikov},
     title = {Martingale models of stochastic approximation and their convergence},
     journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
     pages = {278--311},
     year = {1999},
     volume = {44},
     number = {2},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/TVP_1999_44_2_a2/}
}
TY  - JOUR
AU  - E. Valkeila
AU  - A. V. Melnikov
TI  - Martingale models of stochastic approximation and their convergence
JO  - Teoriâ veroâtnostej i ee primeneniâ
PY  - 1999
SP  - 278
EP  - 311
VL  - 44
IS  - 2
UR  - http://geodesic.mathdoc.fr/item/TVP_1999_44_2_a2/
LA  - ru
ID  - TVP_1999_44_2_a2
ER  - 
%0 Journal Article
%A E. Valkeila
%A A. V. Melnikov
%T Martingale models of stochastic approximation and their convergence
%J Teoriâ veroâtnostej i ee primeneniâ
%D 1999
%P 278-311
%V 44
%N 2
%U http://geodesic.mathdoc.fr/item/TVP_1999_44_2_a2/
%G ru
%F TVP_1999_44_2_a2
E. Valkeila; A. V. Melnikov. Martingale models of stochastic approximation and their convergence. Teoriâ veroâtnostej i ee primeneniâ, Tome 44 (1999) no. 2, pp. 278-311. http://geodesic.mathdoc.fr/item/TVP_1999_44_2_a2/