A lower bound for the ELBO of the Bernoulli Variational Autoencoder

A lower bound for the ELBO of the Bernoulli Variational Autoencoder

We consider a variational autoencoder (VAE) for binary data. Our main innovations are an interpretable lower bound for its training objective, a modified initialization and architecture of such a VAE that leads to faster training, and a decision support for finding the appropriate dimension of the l...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sicks, Robert, Korn, Ralf, Schwaar, Stefanie
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Learning
Mathematics - Statistics Theory
Statistics - Machine Learning
Statistics - Theory
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We consider a variational autoencoder (VAE) for binary data. Our main innovations are an interpretable lower bound for its training objective, a modified initialization and architecture of such a VAE that leads to faster training, and a decision support for finding the appropriate dimension of the latent space via using a PCA. Numerical examples illustrate our theoretical result and the performance of the new architecture.
DOI:10.48550/arxiv.2003.11830