Convergence rate of linear two-time-scale stochastic approximation

Details Convergence rate of linear two-time-scale stochastic approximation Convergence rate of linear two-time-scale stochastic approximation

2004-05-14

arxiv.org/abs/math/0405287v1

Annals of Applied Probability 2004, Vol. 14, No. 2, 796-819

Mathematics

Probability

Scientific paper

10.1214/105051604000000116

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.

Affiliated with

Also associated with

No associations

Rating

Convergence rate of linear two-time-scale stochastic approximation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Convergence rate of linear two-time-scale stochastic approximation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Convergence rate of linear two-time-scale stochastic approximation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-671773