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

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.