A New Proportionate Adaptive Filtering Algorithm with Coefficient Reuse and Robustness Against Impulsive Noise

An adaptive algorithm should ideally present high convergence rate, good steady-state performance, and robustness against impulsive noise. Few algorithms can simultaneously meet these requirements. This paper proposes a local and deterministic optimization problem whose solution gives rise to an adaptive algorithm that presents a higher convergence rate in the identification of sparse systems due to the use of the proportionate adaptation technique. In addition, a correntropy-based cost function is employed in order to enhance its robustness against non-Gaussian noise. Finally, the adoption of coefficient reuse approach results in a good system identification performance in steady-state conditions, especially in low SNR scenarios.