English

SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees

Image and Video Processing 2021-06-04 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.2101.09379,
  title  = {SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees},
  author = {Jiaming Liu and Yu Sun and Weijie Gan and Xiaojian Xu and Brendt Wohlberg and Ulugbek S. Kamilov},
  journal= {arXiv preprint arXiv:2101.09379},
  year   = {2021}
}
R2 v1 2026-06-23T22:26:31.027Z