A lower bound for the ELBO of the Bernoulli Variational Autoencoder
This work addresses efficiency and interpretability issues in VAEs for binary data, though it appears incremental as it builds on existing VAE frameworks.
The authors tackled the problem of training variational autoencoders (VAEs) for binary data by developing an interpretable lower bound for the ELBO, a modified initialization and architecture for faster training, and a decision support method using PCA to determine latent space dimension, with numerical examples demonstrating performance improvements.
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.