DOE OSTI · 1822800
SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees
Abstract
Deep unfolding networks have recently gained popularity for 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 simulations on intensity diffraction tomography and sparse-view computed tomography show that SGD-Net can match the performance of the traditional batch network at a fraction of training and testing complexity.Deep unfolding networks have recently gained popularity for 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 simulations on intensity diffraction tomography and sparse-view computed tomography show that SGD-Net can match the performance of the traditional batch network at a fraction of training and testing complexity.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Liu, Jiaming, Sun, Yu, Gan, Weijie, Xu, Xiaojian, Wohlberg, Brendt Egon, Kamilov, Ulugbek. 2021-06-01. SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees. https://doi.org/10.1109/tci.2021.3085534. https://searchnasa.com/record/osti%3A1822800/sgd-net-efficient-model-based-deep-learning-with-theoretical-guarantees
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.