A Robust Deep Unfolded Network for Sparse Signal Recovery from Noisy Binary Measurements

Y. Yang; P. Xiao; B. Liao; N. Deligiannis

paper

A Robust Deep Unfolded Network for Sparse Signal Recovery from Noisy Binary Measurements

arXiv:2010.07564

Abstract

We propose a novel deep neural network, coined DeepFPC- $ℓ_{2}$ , for solving the 1-bit compressed sensing problem. The network is designed by unfolding the iterations of the fixed-point continuation (FPC) algorithm with one-sided $ℓ_{2}$ -norm (FPC- $ℓ_{2}$ ). The DeepFPC- $ℓ_{2}$ method shows higher signal reconstruction accuracy and convergence speed than the traditional FPC- $ℓ_{2}$ algorithm. Furthermore, we compare its robustness to noise with the previously proposed DeepFPC network---which stemmed from unfolding the FPC- $ℓ_{1}$ algorithm---for different signal to noise ratio (SNR) and sign-flipped ratio (flip ratio) scenarios. We show that the proposed network has better noise immunity than the previous DeepFPC method. This result indicates that the robustness of a deep-unfolded neural network is related with that of the algorithm it stems from.

5 pages, 5 figures, conference