Adaptive error-constrained method for LMS algorithms and applications

An adaptive error-constrained least mean square (AECLMS) algorithm is derived and proposed using adaptive error-constrained optimization techniques. This is accomplished by modifying the cost function of the LMS algorithm using augmented Lagrangian multipliers. Theoretical analyses of the proposed method are presented in detail. The method shows improved performance in terms of convergence speed and misadjustment. This proposed adaptive error-constrained method can easily be applied to and combined with other LMS-type stochastic algorithms. Therefore, we also apply the method to constant modulus criterion for blind method and backpropagation algorithm for multilayer perceptrons. Simulation results show that the proposed method can accelerate the convergence speed by 2 to 20 times depending on the complexity of the problem.