A New Variable Step-Size LMS Adaptive Algorithm Based on Marr Function

Although the traditional LMS algorithm has many advantages, such as simple methods and small burden in computation but for the sake of constant step, it has always contradiction in relationship between solving the steady-state error and convergence. To solve the problem that it is difficult for the traditional LMS adaptive filtering algorithm to solve the conflict between convergence and steady-state error. a new variable step-size LMS algorithm based on Marr function is proposed, along with the performance analysis with regard to different parameters. The theoretical analysis and simulation results show that, the convergence speed and steady error of this algorithm are better than SVS-LMS algorithm and GSVS-LMS algorithm.