The Learned Inexact Project Gradient Descent Algorithm

Raja Giryes, Yonina C. Eldar, Alexander M. Bronstein, Guillermo Sapiro

Abstract

Accelerating iterative algorithms for solving inverse problems using neural networks have become a very popular strategy in the recent years. In this work, we propose a theoretical analysis that may provide an explanation for its success. Our theory relies on the usage of inexact projections with the projected gradient descent (PGD) method. It is demonstrated in various problems including image super-resolution.
BibTeX
@inproceedings{giryes2018learned,
  author = {Raja Giryes and Yonina C. Eldar and Alexander M. Bronstein and Guillermo Sapiro},
  title = {{The Learned Inexact Project Gradient Descent Algorithm}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2018},
  doi = {10.1109/icassp.2018.8462136},
}

Loading related content...

Figure