Toeplitz-Hermitian ADMM-Net for DoA Estimation

TL;DR

This paper introduces THADMM-Net, a deep unfolding neural network for DoA estimation that leverages Toeplitz-Hermitian and positive semi-definite constraints, reducing parameters and outperforming existing methods in accuracy and detection.

Contribution

The paper proposes a novel deep unfolding network with constrained learnable matrices for improved DoA estimation, reducing parameter count and enhancing performance.

Findings

Outperforms Toeplitz-Lista in MSE and detection rate

Reduces parameter count from N^2 to approximately N per layer

Achieves better accuracy over a wide SNR range

Abstract

This paper presents Toeplitz-Hermitian ADMM-Net (THADMM-Net), a deep neural network obtained by deep unfolding the alternating direction method of multipliers (ADMM) algorithm for solving the least absolute shrinkage thresholding operator problem in the context of direction of arrival estimation. By imposing both a Toeplitz-Hermitian as well as positve semi-definite constraint on the learnable matrices, the total parameter count required per layer is reduced from $N^2$ to approximately $N$ where $N$ is the length of the dictionary used in the sparse recovery problem. Numerical simulations show that with a lower parameter count and depth, THADMM-Net outperforms Toeplitz-Lista with respect to the normalized mean-squared error, the detection rate, as well as the root mean-squared error over a signal-to-noise ratio between 0 dB and 35 dB.