Loss Landscapes of Regularized Linear Autoencoders

Autoencoders are a deep learning model for representation learning. When trained to minimize the distance between the data and its reconstruction, linear autoencoders (LAEs) learn the subspace spanned by the top principal directions but cannot learn the principal directions themselves. In this paper...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2019-05
Hauptverfasser:	Kunin, Daniel, Bloom, Jonathan M, Goeva, Aleksandrina, Seed, Cotton
Format:	Artikel
Sprache:	eng
Schlagworte:	Bayesian analysis Euclidean geometry Landscape Machine learning Orthogonality Regularization
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!