Find in Library

Abstract Block‐sparse signals, whose non‐zero entries appear in clusters, have received much attention recently. An unfolded network, named Ada‐BlockLISTA, was proposed to recover a block‐sparse signal at a small computational cost, which learns an individual weight matrix for each block. However, as the number of network parameters is increasingly associated with the number of blocks, the demand for parameter reduction becomes very significant, especially for large‐scale multidimensional harmonic retrieval (MHR) problems. Based on the dictionary characteristics in two‐dimensional (2D) harmonic retrieve problems, the authors introduce a weight coupling structure to shrink Ada‐BlockLISTA, which significantly reduces the number of weights without performance degradation. In simulations, the proposed block‐sparse reconstruction network, named AdaBLISTA‐CP, shows excellent recovery performance with a smaller number of learned parameters.