Stochastic gradient descent for reducing complexity in millimeter wave hybrid precoding design

Abstract

Millimeter wave (mmWave) system tends to have a large number of antenna elements to compensate for the high channel path loss. This paper addresses the computational problem in the hybrid precoding design with large antenna arrays. Orthogonal Matching Pursuit (OMP) based on Stochastic Gradient Descent (SGD) is proposed in this paper. The proposed algorithm exhibits reduced complexity of the signal recovery instead of Least Square (LS) optimization. The simulation results show that a close performance, in terms of spectral efficiency, to the unconstrained optimal precoding case can be achieved with minimizing a cost function.