A Newton-type Forward Backward Greedy method for multi-snapshot compressed sensing

Parameter estimation has applications in many applications of signal processing, such as Angle-of-Arrival (AoA) estimation. Compressed sensing is a widely growing paradigm that can be applied to parameter estimation via sparse recovery. In this paper, we propose a Newton-type Forward Backward Greedy method that performs sparse recovery, given the observed data over multiple snapshots. This method is applied to the AoA estimation problem, where we have observed better performance, in terms of Mean-Squared Error and faster convergence when compared to existing methods. More information can be found in the conclusions section.