Title :
On the boundedness problem of stochastic adaptive algorithms
Author_Institution :
Sch. of Electr. Eng. & Telecommun., Univ. of New South Wales, Sydney, NSW, Australia
Abstract :
The analysis of stochastic adaptive algorithms has been dogged by a boundedness problem from the beginning. While it has been overcome in specific cases it continues to be the achilles heel of general proof methods. Here we provide a new and simple projection method which overcomes these problems. We demonstrate this by finite time averaging analysis for both single time-scale and mixed time- scale, fixed gain, nonlinear algorithms.
Keywords :
adaptive systems; nonlinear systems; stochastic processes; stochastic systems; achilles heel; finite time averaging analysis; general proof methods; nonlinear algorithms; projection method; stochastic adaptive algorithms; Adaptive algorithm; Algorithm design and analysis; Books; Convergence; Markov processes; Monitoring; Parameter estimation; Performance analysis; Stability analysis; Stochastic processes;
Conference_Titel :
Decision and Control, 2009 held jointly with the 2009 28th Chinese Control Conference. CDC/CCC 2009. Proceedings of the 48th IEEE Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-3871-6
Electronic_ISBN :
0191-2216
DOI :
10.1109/CDC.2009.5400114
