English

Deep learning for gradient flows using the Brezis-Ekeland principle

Numerical Analysis 2023-03-01 v1 Machine Learning Numerical Analysis

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.

Keywords

Cite

@article{arxiv.2209.14115,
  title  = {Deep learning for gradient flows using the Brezis-Ekeland principle},
  author = {Laura Carini and Max Jensen and Robert Nürnberg},
  journal= {arXiv preprint arXiv:2209.14115},
  year   = {2023}
}

Comments

Proceeding of the Equadiff 15 conference (https://conference.math.muni.cz/equadiff15)

R2 v1 2026-06-28T02:17:28.051Z