A Generalised Linear Model Framework for β-Variational Autoencoders based on Exponential Dispersion Families

Although variational autoencoders (VAE) are successfully used to obtain meaningful low-dimensional representations for high-dimensional data, the characterization of critical points of the loss function for general observation models is not fully understood. We introduce a theoretical framework that...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Sicks, Robert, Korn, Ralf, Schwaar, Stefanie
Format:	Artikel
Sprache:	eng
Schlagworte:	EDF observation models loss analysis ML-estimation posterior collapse variational autoencoders
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!