Stochastic approximation with averaging and feedback: rapidly convergent "on-line" algorithms
- 1 January 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 40 (1) , 24-34
- https://doi.org/10.1109/9.362902
Abstract
Consider the stochastic approximation X/sub n+1/=X/sub n/+a/sub n/g(X/sub n/, /spl xi//sub n/), where 0 0. The averaging method is essentially "off line" in the sense that the actual SA iterate X/sub n/ is not influenced by the averaging. In many applications, X/sub n/ itself is of greatest interest, since that is the "operating parameter". This paper deals with the problem of stochastic approximation with averaging and with appropriate feedback of the averages into the original algorithm. It is shown both mathematically and via simulation that it works very well and has numerous advantages. It is a clear improvement over the system X/sub n/ by itself. It is fairly robust, and quite often it is much preferable to the use of the above averages without feedback. The authors deal, in particular, with "linear" algorithms of the type appearing in parameter estimators, adaptive noise cancellers, channel equalizers, adaptive control, and similar applications. The main development is for the constant parameter case because of its importance in applications. But analogous results hold for the case where a/sub n//spl rarr/0.Keywords
This publication has 9 references indexed in Scilit:
- Tracking performance analysis of the forgetting factor RLS algorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Stochastic Approximation with Averaging of the Iterates: Optimal Asymptotic Rate of Convergence for General ProcessesSIAM Journal on Control and Optimization, 1993
- Acceleration of Stochastic Approximation by AveragingSIAM Journal on Control and Optimization, 1992
- On extensions of Polyak's averaging approach to stochastic approximationStochastics and Stochastic Reports, 1991
- Adaptive Algorithms and Stochastic ApproximationsPublished by Springer Nature ,1990
- Asymptotic Properties of Distributed and Communicating Stochastic Approximation AlgorithmsSIAM Journal on Control and Optimization, 1987
- Markov ProcessesPublished by Wiley ,1986
- Weak convergence and asymptotic properties of adaptive filters with constant gainsIEEE Transactions on Information Theory, 1984
- Stochastic Approximation Methods for Constrained and Unconstrained SystemsPublished by Springer Nature ,1978