erformance of the Forgetting Factor RLS duri Transient Phase
George V. Moustakides · 1996
consider the convergence properties of the forgetting factor IUS algorithm in a stationary data environment. We study the dependence of the speed of convergence of RLS with respect to the initialization of the input sample covariance matrix and with respect to the observation noise level. By obtaining estimates of the settling time we show that RLS, in a high SNR environment, when initialized with a matrix of small norm, has a very fast convergence. Convergence speed decreases as we increase the norm of the in~t~~~ation matrix. In a medium SNR enviro ent the optim~m d of the ~gorithm is reduced, becomes more insensitive to initializaa low SNR environment it is eferable to start the ~gorith~ with a matrix