A Deep Learning Approach to Structured Signal Recovery

TL;DR

This paper introduces a deep learning framework using stacked denoising autoencoders for structured signal recovery, offering advantages over traditional compressive sensing methods in handling nonlinear measurements and learning from data.

Contribution

It presents a novel deep learning approach that supports nonlinear measurements and learns structured representations, improving recovery performance over classical methods.

Findings

Outperforms traditional CS in structured signal recovery

Supports nonlinear measurement models

Efficiently learns from training data

Abstract

In this paper, we develop a new framework for sensing and recovering structured signals. In contrast to compressive sensing (CS) systems that employ linear measurements, sparse representations, and computationally complex convex/greedy algorithms, we introduce a deep learning framework that supports both linear and mildly nonlinear measurements, that learns a structured representation from training data, and that efficiently computes a signal estimate. In particular, we apply a stacked denoising autoencoder (SDA), as an unsupervised feature learner. SDA enables us to capture statistical dependencies between the different elements of certain signals and improve signal recovery performance as compared to the CS approach.