Model-Aware Deep Architectures for One-Bit Compressive Variational Autoencoding

Abstract

Parameterized mathematical models play a central role in understanding and design of complex information systems. However, they often cannot take into account the intricate interactions innate to such systems. On the contrary, purely data-driven approaches do not need explicit mathematical models for data generation and have a wider applicability at the cost of interpretability. In this paper, we consider the design of a one-bit compressive variational autoencoder, and propose a novel hybrid model-based and data-driven methodology that allows us not only to design the sensing matrix and the quantization thresholds for one-bit data acquisition, but also allows for learning the latent-parameters of iterative optimization algorithms specifically designed for the problem of one-bit sparse signal recovery. In addition, the proposed method has the ability to adaptively learn the proper quantization thresholds, paving the way for amplitude recovery in one-bit compressive sensing. Our results demonstrate a significant improvement compared to state-of-the-art model-based algorithms.

References in corpus (8)

• Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
• A Comparison of Hybrid Beamforming and Digital Beamforming with Low-Resolution ADCs for Multiple Users and Imperfect CSI
• One-Bit Radar Processing with Time-Varying Sampling Thresholds
• Deep Signal Recovery with One-Bit Quantization
• Deep Compressed Sensing
• Opportunistic Collaborative Beamforming with One-Bit Feedback
• Spectral Efficiency of One-Bit Sigma-Delta Massive MIMO
• Signal Recovery From 1-Bit Quantized Noisy Samples via Adaptive Thresholding

Cited by in corpus (5)

• Review: Deep Learning in Electron Microscopy
• Efficient Waveform Covariance Matrix Design and Antenna Selection for MIMO Radar
• Deep-URL: A Model-Aware Approach To Blind Deconvolution Based On Deep Unfolded Richardson-Lucy Network
• Deep Radar Waveform Design for Efficient Automotive Radar Sensing
• Deep-RLS: A Model-Inspired Deep Learning Approach to Nonlinear PCA