Convergence rate of linear two-time-scale stochastic approximation
Probability
2009-09-29 v1
Abstract
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.
Cite
@article{arxiv.math/0405287,
title = {Convergence rate of linear two-time-scale stochastic approximation},
author = {Vijay R. Konda and John N. Tsitsiklis},
journal= {arXiv preprint arXiv:math/0405287},
year = {2009}
}