GILBO: One Metric to Measure Them All
Machine Learning
2019-01-11 v3 Machine Learning
Abstract
We propose a simple, tractable lower bound on the mutual information contained in the joint generative density of any latent variable generative model: the GILBO (Generative Information Lower BOund). It offers a data-independent measure of the complexity of the learned latent variable description, giving the log of the effective description length. It is well-defined for both VAEs and GANs. We compute the GILBO for 800 GANs and VAEs each trained on four datasets (MNIST, FashionMNIST, CIFAR-10 and CelebA) and discuss the results.
Keywords
Cite
@article{arxiv.1802.04874,
title = {GILBO: One Metric to Measure Them All},
author = {Alexander A. Alemi and Ian Fischer},
journal= {arXiv preprint arXiv:1802.04874},
year = {2019}
}
Comments
Accepted at NeurIPS 2018