Hassibi, Babak and Kailath, Thomas (1994) H^∞ bounds for the recursive-least-squares algorithm. In: Proceedings of the 33rd IEEE Conference on Decision and Control, 1994. Vol.4. IEEE , Piscataway, NJ, pp. 3927-3928. ISBN 0-7803-1968-0. https://resolver.caltech.edu/CaltechAUTHORS:20150219-072113191
![]() |
PDF
- Published Version
See Usage Policy. 190Kb |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20150219-072113191
Abstract
We obtain upper and lower bounds for the H^∞ norm of the RLS (recursive-least-squares) algorithm. The H^∞ norm may be regarded as the worst-case energy gain from the disturbances to the prediction errors, and is therefore a measure of the robustness of an algorithm to perturbations and model uncertainty. Our results allow one to compare the robustness of RLS compared to the LMS (least-mean-squares) algorithm, which is known to minimize the H^∞ norm. Simulations are presented to show the behaviour of RLS relative to these bounds.
Item Type: | Book Section | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
Related URLs: |
| |||||||||
Additional Information: | © 1994 IEEE. This research was supported by the Advanced Research Projects Agency of the Department of Defense monitored by the Air Force Office of Scientific Research under Contract F4962G93-1-008. | |||||||||
Funders: |
| |||||||||
Record Number: | CaltechAUTHORS:20150219-072113191 | |||||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20150219-072113191 | |||||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | |||||||||
ID Code: | 54973 | |||||||||
Collection: | CaltechAUTHORS | |||||||||
Deposited By: | Shirley Slattery | |||||||||
Deposited On: | 03 Mar 2015 02:42 | |||||||||
Last Modified: | 03 Oct 2019 08:02 |
Repository Staff Only: item control page