Deep-Unfolded Adaptive Projected Subgradient Method For Mimo Detection

In this paper, we propose deep-unfolded versions of the recently proposed superiorized adaptive projected subgradient method for MIMO detection. The proposed methods require a single matrix inverse for initialization, and they have a quadratic per-iteration complexity. Extensive simulations with realistic channel models show that the proposed deep-unfolded detectors outperform not only their untrained counterpart, but also existing methods with similar complexity.