Scarlett, Jonathan;
Heckel, Reinhard;
Rodrigues, Miguel RD;
Hand, Paul;
Eldar, Yonina C;
(2023)
Theoretical Perspectives on Deep Learning Methods in Inverse Problems.
IEEE Journal on Selected Areas in Information Theory
10.1109/jsait.2023.3241123.
![]() |
Text
Theoretical_Perspectives_on_Deep_Learning_Methods_in_Inverse_Problems.pdf - Accepted Version Download (1MB) |
Abstract
In recent years, there have been significant advances in the use of deep learning methods in inverse problems such as denoising, compressive sensing, inpainting, and super-resolution. While this line of works has predominantly been driven by practical algorithms and experiments, it has also given rise to a variety of intriguing theoretical problems. In this paper, we survey some of the prominent theoretical developments in this line of works, focusing in particular on generative priors, untrained neural network priors, and unfolding algorithms. In addition to summarizing existing results in these topics, we highlight several ongoing challenges and open problems.
Type: | Article |
---|---|
Title: | Theoretical Perspectives on Deep Learning Methods in Inverse Problems |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1109/jsait.2023.3241123 |
Publisher version: | https://doi.org/10.1109/JSAIT.2023.3241123 |
Language: | English |
Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
Keywords: | Inverse problems, generative priors, untrained neural networks, unfolding algorithms, compressive sensing, denoising, theoretical guarantees, information-theoretic limits. |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
URI: | https://discovery.ucl.ac.uk/id/eprint/10166021 |
Archive Staff Only
![]() |
View Item |