ADMM for harmonic retrieval from one-bit sampling with time-varying thresholds

Abstract

Parameter estimation of sinusoids is a problem of significance in many practical applications. This problem is revisited through a new alternating direction method of multipliers (ADMM) based approach, where the unknown parameters are estimated from one-bit quantized noisy measurements with time varying thresholds. The proposed method is computationally efficient and easy to implement, since each ADMM update has simple closed-form formula. Moreover, it provides accurate estimates by exploiting group sparsity hidden in the signal model. Simulations demonstrate the effectiveness of our algorithm.