Title :
On statistical efficiency of the LMS algorithm in system modeling
Author :
Farhang-Boroujeny, B.
Author_Institution :
Dept. of Electr. Eng., Nat. Univ. of Singapore, Singapore
fDate :
5/1/1993 12:00:00 AM
Abstract :
The conventional least-mean-square (LMS) algorithm is compared with the ideal LMS/Newton (ILMSN) algorithm. It is shown that, although under certain conditions, for similar misadjustment, the output mean-square error (MSE) of the ILMSN algorithm may converge much faster than the MSE of the LMS algorithm, the difference between the two algorithms may not be that great if misalignments of the adaptive filter tap gains are compared. Analytical results are presented, with computer simulations that support their validity
Keywords :
adaptive systems; filtering and prediction theory; least squares approximations; LMS/Newton algorithm; MSE; adaptive filter tap gains; computer simulations; convergence; least mean square algorithm; output mean-square error; statistical efficiency; system modeling; Adaptive filters; Adaptive signal processing; Convergence; Degradation; Least squares approximation; Least squares methods; Modeling; Signal processing; Signal processing algorithms; Speech processing;
Journal_Title :
Signal Processing, IEEE Transactions on
