LGMLAug 2, 2018

Variational Information Bottleneck on Vector Quantized Autoencoders

arXiv:1808.01048v16 citations
Originality Synthesis-oriented
AI Analysis

This provides an information-theoretic interpretation for VQ-VAE, which is incremental as it explains an existing method without introducing new performance gains.

The paper tackles the problem of interpreting the Vector Quantized-Variational Autoencoder (VQ-VAE) by showing that its loss function can be derived from the variational deterministic information bottleneck principle, and that its EM-trained version approximates the variational information bottleneck principle.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes