A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions
Jentzen, Arnulf; Riekert, Adrian
Research article (journal) | Peer reviewedDetails about the publication
Journal: Zeitschrift für Angewandte Mathematik und Physik
Volume: 73
Issue: 5
Article number: 188
Status: Published
Release year: 2022
Language in which the publication is written: English
Link to the full text: https://link.springer.com/article/10.1007/s00033-022-01716-w
Keywords: Artificial intelligence; Neural networks; Stochastic gradient descent; Non-convex optimization
Authors from the University of Münster
| Jentzen, Arnulf | Institute for Analysis and Numerics |
| Riekert, Adrian | Mathematical Institute |