Low-Complexity Vector Quantized Compressed Sensing via Deep Neural Networks

TL;DR

This paper introduces a deep neural network-based approach for low-complexity vector quantized compressed sensing, improving signal reconstruction accuracy and efficiency in resource-limited, delay-sensitive applications.

Contribution

It presents a novel deep encoder-decoder architecture for vector quantized compressed sensing, trained via supervised learning to optimize rate-distortion performance.

Findings

Outperforms standard QCS methods in rate-distortion trade-offs

Achieves lower algorithm complexity

Suitable for large-scale, delay-sensitive applications

Abstract

Sparse signals, encountered in many wireless and signal acquisition applications, can be acquired via compressed sensing (CS) to reduce computations and transmissions, crucial for resource-limited devices, e.g., wireless sensors. Since the information signals are often continuous-valued, digital communication of compressive measurements requires quantization. In such a quantized compressed sensing (QCS) context, we address remote acquisition of a sparse source through vector quantized noisy compressive measurements. We propose a deep encoder-decoder architecture, consisting of an encoder deep neural network (DNN), a quantizer, and a decoder DNN, that realizes low-complexity vector quantization aiming at minimizing the mean-square error of the signal reconstruction for a given quantization rate. We devise a supervised learning method using stochastic gradient descent and backpropagation to train the system blocks. Strategies to overcome the vanishing gradient problem are proposed. Simulation results show that the proposed non-iterative DNN-based QCS method achieves higher rate-distortion performance with lower algorithm complexity as compared to standard QCS methods, conducive to delay-sensitive applications with large-scale signals.