New low-rank optimization model and algorithms for spectral compressed sensing

In this paper, we investigate the recovery of an undamped spectrally sparse signal and its spectral components from a set of regularly spaced samples within the framework of spectral compressed sensing and super-resolution. We show that the existing Hankel-based optimization methods suffer from the fundamental limitation that the prior knowledge of undampedness cannot be exploited. We propose a new low-rank optimization model partially inspired by forward-backward processing for line spectral estimation and show its capability to restrict the spectral poles to the unit circle. We present convex relaxation approaches with the model and show their provable accuracy and robustness to bounded and sparse noise. All our results are generalized from one-dimensional to arbitrary-dimensional spectral compressed sensing. Numerical simulations are provided to corroborate our analysis and show the efficiency of our model and the advantageous performance of our approach in terms of accuracy and resolution compared with the state-of-the-art Hankel and atomic norm methods.