Title :
Almost sure rate of convergence of the parameter estimates in stochastic approximation algorithm
Author :
Radenkovic, Miloje S ; Michel, A.N.
Author_Institution :
Dept. of Electr. Eng., Colorado Univ., Denver, CO
fDate :
6/1/2000 12:00:00 AM
Abstract :
This paper presents novel results on the almost sure convergence of the parameter estimates in stochastic approximation algorithm. It is proved that this rate has the same order as the best one established for the least squares algorithm. Although we consider the case of self-tuning controllers, the presented results can easily be extended to some other adaptive processes
Keywords :
approximation theory; convergence; discrete time systems; parameter estimation; self-adjusting systems; stochastic processes; SISO systems; almost sure convergence; discrete time systems; martingale; parameter estimation; self-tuning controller; stochastic approximation; Adaptive control; Adaptive systems; Approximation algorithms; Convergence; Error correction; Least squares approximation; Least squares methods; Parameter estimation; Programmable control; Stochastic processes;
Journal_Title :
Automatic Control, IEEE Transactions on
