Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algorithms
Mokkadem, Abdelkader ; Pelletier, Mariane
Ann. Appl. Probab., Tome 16 (2006) no. 1, p. 1671-1702 / Harvested from Project Euclid
The first aim of this paper is to establish the weak convergence rate of nonlinear two-time-scale stochastic approximation algorithms. Its second aim is to introduce the averaging principle in the context of two-time-scale stochastic approximation algorithms. We first define the notion of asymptotic efficiency in this framework, then introduce the averaged two-time-scale stochastic approximation algorithm, and finally establish its weak convergence rate. We show, in particular, that both components of the averaged two-time-scale stochastic approximation algorithm simultaneously converge at the optimal rate $\sqrt{n}$ .
Publié le : 2006-08-14
Classification:  Stochastic approximation,  two-time-scales,  weak convergence rate,  averaging principle,  62L20
@article{1159804996,
     author = {Mokkadem, Abdelkader and Pelletier, Mariane},
     title = {Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algorithms},
     journal = {Ann. Appl. Probab.},
     volume = {16},
     number = {1},
     year = {2006},
     pages = { 1671-1702},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1159804996}
}
Mokkadem, Abdelkader; Pelletier, Mariane. Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algorithms. Ann. Appl. Probab., Tome 16 (2006) no. 1, pp.  1671-1702. http://gdmltest.u-ga.fr/item/1159804996/