Physically constrained unfolded multi-dimensional OMP for large MIMO systems

TL;DR

This paper introduces MOMPnet, a deep unfolding framework combining data-driven dictionary learning and a multidimensional OMP algorithm to improve sparse recovery in large MIMO systems, addressing reliability and complexity issues.

Contribution

It presents a novel unfolded sparse recovery method that integrates deep learning with physical models, using multiple dictionaries for low complexity in large MIMO systems.

Findings

Demonstrates strong performance on realistic channel data.

Mitigates hardware impairments effectively.

Reduces computational complexity with multiple smaller dictionaries.

Abstract

Sparse recovery methods are essential for channel estimation and localization in modern communication systems, but their reliability relies on accurate physical models, which are rarely perfectly known. Their computational complexity also grows rapidly with the dictionary dimensions in large MIMO systems. In this paper, we propose MOMPnet, a novel unfolded sparse recovery framework that addresses both the reliability and complexity challenges of traditional methods. By integrating deep unfolding with data-driven dictionary learning, MOMPnet mitigates hardware impairments while preserving interpretability. Instead of a single large dictionary, multiple smaller, independent dictionaries are employed, enabling a low-complexity multidimensional Orthogonal Matching Pursuit algorithm. The proposed unfolded network is evaluated on realistic channel data against multiple baselines, demonstrating its strong performance and potential.