Convergence to good non-optimal critical points in the training of neural networks: Gradient descent optimization with one random initialization overcomes all bad non-global local minima with high probability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ibragimov, Shokhrukh, Jentzen, Arnulf, Riekert, Adrian
Format:	Preprint
Published:	2022
Subjects:	Optimization and Control 65K10, 65C50, 68T05, 60H35
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2212.13111