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

arXiv1911.12410MaRDI QIDQ6329997

Author name not available (Why is that?)

Publication date: 27 November 2019

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.

Has companion code repository: https://github.com/skhobahi/deep1bitVAE

This page was built for publication: Model-Aware Deep Architectures for One-Bit Compressive Variational Autoencoding

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6329997)