In this paper, we provide an information-theoretic interpretation of the Vector Quantized-Variational Autoencoder (VQ-VAE). We show that the loss function of the original VQ-VAE can be derived from the variational deterministic information bottleneck (VDIB) principle. On the other hand, the VQ-VAE trained by the Expectation Maximization (EM) algorithm can be viewed as an approximation to the variational information bottleneck(VIB) principle.
@article{arxiv.1808.01048,
title = {Variational Information Bottleneck on Vector Quantized Autoencoders},
author = {Hanwei Wu and Markus Flierl},
journal= {arXiv preprint arXiv:1808.01048},
year = {2018}
}