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.
@article{arxiv.2003.11830,
title = {A lower bound for the ELBO of the Bernoulli Variational Autoencoder},
author = {Robert Sicks and Ralf Korn and Stefanie Schwaar},
journal= {arXiv preprint arXiv:2003.11830},
year = {2020}
}