The Learned Inexact Project Gradient Descent Algorithm

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6767-6771
Number of pages5
ISBN (Electronic)9781538646588, 9781538646571
ISBN (Print)9781538646588, 9781538646595
DOIs
StatePublished - 10 Sep 2018
Event2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Calgary, Canada
Duration: 15 Apr 201820 Apr 2018

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2018-April

Conference

Conference2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
Country/TerritoryCanada
CityCalgary
Period15/04/1820/04/18

Keywords

  • Algorithm Acceleration
  • Deep Learning
  • Inverse Problems
  • LISTA
  • Sparse Representation

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'The Learned Inexact Project Gradient Descent Algorithm'. Together they form a unique fingerprint.

Cite this