Loss landscapes and optimization in over-parameterized non-linear systems and neural networks

The success of deep learning is due, to a large extent, to the remarkable effectiveness of gradient-based optimization methods applied to large neural networks. The purpose of this work is to propose a modern view and a general mathematical framework for loss landscapes and efficient optimization in...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Applied and computational harmonic analysis Jg. 59; S. 85 - 116
Hauptverfasser:	Liu, Chaoyue, Zhu, Libin, Belkin, Mikhail
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Inc 01.07.2022
Schlagworte:	Deep learning Non-linear optimization Over-parameterized models PL⁎ condition Deep learning PL⁎ condition Over-parameterized models Non-linear optimization
ISSN:	1063-5203
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!