brendt.wohlberg.net
HomePublications
› Publications
› Software

Cite Details

Jiaming Liu, Yu Sun, Weijie Gan, Xiaojian Xu, Brendt Wohlberg and Ulugbek S. Kamilov, "SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees", arXiv, 2101.09379, 2021

Abstract

Deep unfolding networks have recently gained popularity in the context of solving imaging inverse problems. However, the computational and memory complexity of data-consistency layers within traditional deep unfolding networks scales with the number of measurements, limiting their applicability to large-scale imaging inverse problems. We propose SGD-Net as a new methodology for improving the efficiency of deep unfolding through stochastic approximations of the data-consistency layers. Our theoretical analysis shows that SGD-Net can be trained to approximate batch deep unfolding networks to an arbitrary precision. Our numerical results on intensity diffraction tomography and sparse-view computed tomography show that SGD-Net can match the performance of the batch network at a fraction of training and testing complexity.

BibTeX Entry

@techreport{liu-2021-sgdnet,
author = {Jiaming Liu and Yu Sun and Weijie Gan and Xiaojian Xu and Brendt Wohlberg and Ulugbek S. Kamilov},
title = {{SGD-Net}: Efficient Model-Based Deep Learning with Theoretical Guarantees},
year = {2021},
month = Jan,
urlpdf = {http://arxiv.org/pdf/2101.09379},
urlhtml = {http://arxiv.org/abs/2101.09379},
institution = {arXiv},
number = {2101.09379}
}