Thermodynamic Natural Gradient Descent

Second-order training methods have better convergence properties than gradient descent but are rarely used in practice for large-scale training due to their computational overhead. This can be viewed as a hardware limitation (imposed by digital computers). Here we show that natural gradient descent...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Donatella, Kaelan, Duffield, Samuel, Aifer, Maxwell, Melanson, Denis, Crooks, Gavin, Coles, Patrick J
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Emerging Technologies Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!