Title :
NSLMS: a proportional weight algorithm for sparse adaptive filters
Author :
Martin, R.K. ; Johnson, C.R., Jr.
Author_Institution :
Sch. of Electr. Eng., Cornell Univ., Ithaca, NY, USA
Abstract :
We discuss a proportional weight algorithm that is similar to least mean square (LMS). The distinction is that the new algorithm (called normalized sparse LMS, or NSLMS) has a time-varying vector step size, whose coefficients are proportional to the magnitudes of the current values of the tap estimates. We show that when the system to be identified is sparse, NSLMS converges faster than LMS (to the same asymptotic MMSE for both algorithms). We also discuss the effect of the initialization on the performance of NSLMS.
Keywords :
adaptive equalisers; adaptive filters; adaptive signal processing; convergence of numerical methods; filtering theory; least mean squares methods; LMS; NSLMS; asymptotic MMSE; channel equalization; channel identification; coefficients; complexity; convergence; initialization; least mean square algorithm; normalized sparse LMS; proportional weight algorithm; sparse adaptive filters; tap estimates; time-varying vector step size; Adaptive filters; Costs; Echo cancellers; Equalizers; Finite impulse response filter; Least squares approximation; Performance loss; Signal generators; Underwater acoustics;
Conference_Titel :
Signals, Systems and Computers, 2001. Conference Record of the Thirty-Fifth Asilomar Conference on
Conference_Location :
Pacific Grove, CA, USA
Print_ISBN :
0-7803-7147-X
DOI :
10.1109/ACSSC.2001.987743
