Theoretical Perspectives on Deep Learning Methods in Inverse Problems
From MaRDI portal
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.
This page was built for publication: Theoretical Perspectives on Deep Learning Methods in Inverse Problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6403477)
