Crossmark

A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions

Crossref DOI link: https://doi.org/10.1007/s00033-022-01716-w

Published Online: 2022-08-09

Published Print: 2022-10

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Jentzen, Arnulf http://orcid.org/0000-0002-9840-3339
Riekert, Adrian http://orcid.org/0000-0002-1458-3388
Funding

Funding for this research was provided by:

Deutsche Forschungsgemeinschaft (EXC 2044-390685587)
License Information

Text and Data Mining valid from 2022-08-09

Version of Record valid from 2022-08-09
More Information

Article History

Received: 13 April 2021

Revised: 9 February 2022

Accepted: 13 February 2022

First Online: 9 August 2022

Change Date: 3 November 2022

Change Type: Update

Change Details: Missing Open Access funding information has been added in the Funding Note.

Declarations

:

: The authors declare that they have no conflict of interest.

: Not applicable.

Document is current

Any future updates will be listed below