Convergence rate of linear two-time-scale stochastic approximation
Konda, Vijay R. ; Tsitsiklis, John N.
Ann. Appl. Probab., Tome 14 (2004) no. 1, p. 796-819 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
We study the rate of convergence of linear two-time-scale stochastic approximation methods. We consider two-time-scale linear iterations driven by i.i.d. noise, prove some results on their asymptotic covariance and establish asymptotic normality. The well-known result [Polyak, B. T. (1990). Automat. Remote Contr. 51 937–946; Ruppert, D. (1988). Technical Report 781, Cornell Univ. ] on the optimality of Polyak–Ruppert averaging techniques specialized to linear stochastic approximation is established as a consequence of the general results in this paper.
Publié le : 2004-05-14
Classification:  Stochastic approximation,  two-time-scales,  62L20 
@article{1082737112,
     author = {Konda, Vijay R. and Tsitsiklis, John N.},
     title = {Convergence rate of linear two-time-scale stochastic approximation},
     journal = {Ann. Appl. Probab.},
     volume = {14},
     number = {1},
     year = {2004},
     pages = { 796-819},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1082737112}
}

Konda, Vijay R.; Tsitsiklis, John N. Convergence rate of linear two-time-scale stochastic approximation. Ann. Appl. Probab., Tome 14 (2004) no. 1, pp.  796-819. http://gdmltest.u-ga.fr/item/1082737112/