Skip to yearly menu bar Skip to main content


Poster

GILBO: One Metric to Measure Them All

Alexander Alemi · Ian Fischer

Room 210 #57

Keywords: [ Information Theory ] [ Adversarial Networks ] [ Generative Models ] [ Latent Variable Models ]


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.

Live content is unavailable. Log in and register to view live content