Adaptive stepsize selection for tracking in a non-stationary environment: a new pre-emptive approach

We consider the problem of using a stochastic approximation algorithm to perform online tracking in a non-stationary environment characterized by infrequent and sudden "regime changes". The primary contribution of this paper is a new approach for adaptive stepsize selection that is suitabl...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the 45th IEEE Conference on Decision and Control s. 1817 - 1822
Hlavní autoři: Costa, A., Vazquez-Abad, F.J.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.12.2006
Témata:
Adaptive control
Approximation algorithms
Convergence
Drives
Linear systems
Programmable control
Random variables
Real time systems
regime switching
stochastic approximation
Stochastic processes
tracking
USA Councils
weak convergence
ISBN:9781424401710, 1424401712
ISSN:0191-2216
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We consider the problem of using a stochastic approximation algorithm to perform online tracking in a non-stationary environment characterized by infrequent and sudden "regime changes". The primary contribution of this paper is a new approach for adaptive stepsize selection that is suitable for this type of non-stationarity. Our approach is pre-emptive rather than reactive, and is based on a strategy of maximising the rate of adaptation, subject to a constraint on the probability that the iterates fall outside a pre-determined range of "acceptable error". The theoretical basis for our approach is provided by the theory of weak convergence for stochastic approximation algorithms
ISBN:9781424401710
1424401712
ISSN:0191-2216
DOI:10.1109/CDC.2006.377312