Title :
A variable weight mixed-norm adaptive algorithm
Author :
Zerguine, Azzedine ; Aboulnasr, Tyseer
Author_Institution :
Electrical Engineering Department, King Fahd University of Petroleum & Minerals, Dhahran 31261, Saudi Arabia
Abstract :
The convergence analysis of the variable weight mixed-norm LMS-LMF adaptive algorithm is derived. A novel approach is used to study the convergence behavior of three algorithms: mixed-norm- LMS- and LMF-based ones. As a by-product of this novel approach, more general and new necessary and sufficient conditions and excess steady-state error for the LMF have been derived.
Conference_Titel :
Acoustics, Speech, and Signal Processing (ICASSP), 2002 IEEE International Conference on
Conference_Location :
Orlando, FL, USA
Print_ISBN :
0-7803-7402-9
DOI :
10.1109/ICASSP.2002.5745814
