A fast approximate RLS algorithm

Abstract

Motivated by the real time applications of adaptive signal processing algorithms a new Approximate RLS algorithm is developed. It is shown that the computational complexity of this algorithm is comparable to that of the LMS algorithm. Convergence analysis for this algorithm is presented showing the unconditional convergence of the algorithm in the mean and the mean square sense for stationary data. It is shown that the rate of convergence of this algorithm is n/sup -1/. The convergence characteristics of this algorithm shows that the algorithm is much faster than the LMS algorithm but somewhat slower than the RLS algorithm. Modifications to this algorithm are suggested for use in nonstationary data environment. Simulation results for this algorithm are compared with those for the LMS and the RLS algorithms.<>