Skip to Main Content
A low-complexity implementation of the constrained recursive least squares (CRLS) adaptive filtering algorithm is developed based on the method of weighting and the dichotomous coordinate descent (DCD) iterations. The method of weighting is employed to incorporate the linear constraints into the least squares problem of interest. The DCD iterations are then used to solve the normal equations of the resultant unconstrained least squares problem. The new algorithm has a significantly smaller computational complexity than the CRLS algorithm while delivering convergence performance on par with it. Simulations demonstrate the effectiveness of the proposed algorithm.