Carini, Laura;
Jensen, Max;
Nürnberg, Robert;
(2023)
Deep learning for gradient flows using the Brezis–Ekeland principle.
Archivum Mathematicum
, 59
(3)
pp. 249-261.
10.5817/am2023-3-249.
Preview |
Text
Jensen_main.pdf - Accepted Version Download (566kB) | Preview |
Abstract
We propose a deep learning method for the numerical solution of partial differential equations that arise as gradient flows. The method relies on the Brezis–Ekeland principle, which naturally defines an objective function to be minimized, and so is ideally suited for a machine learning approach using deep neural networks. We describe our approach in a general framework and illustrate the method with the help of an example implementation for the heat equation in space dimensions two to seven.
Type: | Article |
---|---|
Title: | Deep learning for gradient flows using the Brezis–Ekeland principle |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.5817/am2023-3-249 |
Publisher version: | http://dx.doi.org/10.5817/AM2023-3-249 |
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: | Machine learning; deep neural networks; gradient flows; Brezis–Ekeland principle; adversarial networks; differential equations |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Mathematics |
URI: | https://discovery.ucl.ac.uk/id/eprint/10165976 |
Archive Staff Only
View Item |