Avoiding Spurious Local Minima in Deep Quadratic Networks

Despite their practical success, a theoretical understanding of the loss landscape of neural networks has proven challenging due to the high-dimensional, non-convex, and highly nonlinear structure of such models. In this paper, we characterize the training landscape of the mean squared error loss fo...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Kazemipour, Abbas, Larsen, Brett W, Druckmann, Shaul
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Mathematics - Optimization and Control Statistics - Machine Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!