NeurIPS 2018spotlight16 citations
GILBO: One Metric to Measure Them All
Alexander A Alemi, Ian Fischer
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.
BibTeX
@inproceedings{NEURIPS2018_7535bbb9,
author = {Alemi, Alexander A and Fischer, Ian},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {GILBO: One Metric to Measure Them All},
url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/7535bbb91c8fde347ad861f293126633-Paper.pdf},
volume = {31},
year = {2018}
}