Deep Unfolding for MIMO Signal Detection

TL;DR

This paper introduces a novel deep unfolding neural network for MIMO signal detection that operates directly in the complex domain, offering improved performance and efficiency for massive MIMO systems.

Contribution

It presents the DPST algorithm, a complex-valued deep unfolding method with minimal trainable parameters, enhancing detection accuracy and reducing complexity.

Findings

Achieves superior detection performance over existing methods.

Requires fewer iterations and less computational resources.

Operates natively in the complex domain for signal processing.

Abstract

In this paper, we propose a deep unfolding neural network-based MIMO detector that incorporates complex-valued computations using Wirtinger calculus. The method, referred as Dynamic Partially Shrinkage Thresholding (DPST), enables efficient, interpretable, and low-complexity MIMO signal detection. Unlike prior approaches that rely on real-valued approximations, our method operates natively in the complex domain, aligning with the fundamental nature of signal processing tasks. The proposed algorithm requires only a small number of trainable parameters, allowing for simplified training. Numerical results demonstrate that the proposed method achieves superior detection performance with fewer iterations and lower computational complexity, making it a practical solution for next-generation massive MIMO systems.