GILBO: One Metric to Measure Them All

02/13/2018

∙

by   Alexander A. Alemi, et al.

∙

0

∙

share

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 trained on MNIST and discuss the results.