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

TL;DR

This paper introduces DeepFPC-ℓ₂, a deep neural network based on unfolding the FPC-ℓ₂ algorithm, which achieves superior accuracy, faster convergence, and enhanced noise robustness in 1-bit compressed sensing compared to traditional methods.

Contribution

The paper presents a novel deep-unfolded neural network, DeepFPC-ℓ₂, that improves sparse signal recovery from noisy binary measurements by leveraging the fixed-point continuation algorithm.

Findings

DeepFPC-ℓ₂ outperforms traditional FPC-ℓ₂ in accuracy and speed.

The network demonstrates better noise immunity than previous DeepFPC.

Robustness correlates with the underlying algorithm's properties.

Abstract

We propose a novel deep neural network, coined DeepFPC-$\ell_2$, 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 $\ell_2$-norm (FPC-$\ell_2$). The DeepFPC-$\ell_2$ method shows higher signal reconstruction accuracy and convergence speed than the traditional FPC-$\ell_2$ algorithm. Furthermore, we compare its robustness to noise with the previously proposed DeepFPC network---which stemmed from unfolding the FPC-$\ell_1$ 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.