A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target functions
Jentzen, Arnulf; Riekert, Adrian
Research article (journal) | Peer reviewedDetails about the publication
Journal: Journal of Machine Learning Research
Volume: 23
Issue: 260
Page range: 1-50
Status: Published
Release year: 2022
Language in which the publication is written: English
Link to the full text: https://jmlr.org/papers/v23/21-0962.html
Keywords: Gradient descent; Artificial neural networks; Non-convex optimization
Authors from the University of Münster
| Jentzen, Arnulf | Institute for Analysis and Numerics |
| Riekert, Adrian | Mathematical Institute |