Title
A deterministic analysis of stochastic approximation with randomized directions
Abstract
We study the convergence of two stochastic approxima- tion algorithms with randomized directions: the simultaneous pertur- bation stochastic approximation algorithm and the random direction Kiefer-Wolfowitz algorithm. We establish deterministic necessary and sufficient conditions on the random directions and noise sequences for both algorithms, and these conditions demonstrate the effect of the "ran- dom" directions on the "sample-path" behavior of the studied algorithms. We discuss ideas for further research in analysis and design of these algorithms.
Year
DOI
Venue
1998
10.1109/9.736077
IEEE Transactions on Automatic Control
Keywords
DocType
Volume
Stochastic processes,Bifurcation,Surges,Control systems,Asymptotic stability,Lyapunov method,Feedback,Control design,Hysteresis,Backstepping
Journal
43
Issue
ISSN
Citations 
12
0018-9286
12
PageRank 
References 
Authors
1.22
4
2
Name
Order
Citations
PageRank
I-Jeng Wang127731.46
Edwin K. P. Chong21758185.45