Analysis of momentum adaptive filtering algorithms
Authors:
- W.A. SetharesWSW.A. Sethares
- J.A. BucklewJBJ.A. Bucklew
- 1 May 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 46 (5) , 1430-1434
Abstract
This article analyzes the momentum LMS algorithm and other momentum algorithms using asymptotic techniques that provide information regarding the almost sure behavior of the parameter estimates and their asymptotic distribution. The analysis does not make any assumptions on the autocorrelation function of the input processKeywords
This publication has 4 references indexed in Scilit:
- The covering problem and μ-dependent adaptive algorithmsIEEE Transactions on Signal Processing, 1994
- Weak convergence and local stability properties of fixed step size recursive algorithmsIEEE Transactions on Information Theory, 1993
- Analysis of the momentum LMS algorithmIEEE Transactions on Acoustics, Speech, and Signal Processing, 1990
- Channel identification for high speed digital communicationsIEEE Transactions on Automatic Control, 1974