The USC Andrew and Erna Viterbi School of Engineering USC Signal and Image Processing Institute USC Ming Hsieh Department of Electrical Engineering University of Southern California

Technical Report USC-SIPI-280

“New Results on the Mean an Mean Square Convergence of LMS”

by Esmat Bekir and C.-C. Jay Kuo

April 1995

New results on the mean and mean square convergence of the LMS algorithm are presented. First, a new approach is proposed for the derivation of the necessary and sufficient conditions for mean square convergence. Second, we derive an explicit expression on the bound of the step size and show an interesting relationship between the mean and mean square convergence.

To download the report in PDF format click here: USC-SIPI-280.pdf (0.9Mb)