Gradient descent provably escapes saddle points in the training of shallow ReLU networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheridito, Patrick, Jentzen, Arnulf, Rossmannek, Florian
Format:	Preprint
Published:	2022
Subjects:	Machine Learning Dynamical Systems Optimization and Control 68T07, 37D10 I.2.6; G.1.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2208.02083