资源分类
》 资源 》论文》G ILBO: One Metric to Measure Them All

G ILBO: One Metric to Measure Them All

2020-02-14 | |  84 |   82 |   0

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.

上一篇：Stein Variational Gradient Descent as Moment Matching

下一篇：Step Size Matters in Deep Learning

用户评价
全部评价

热门资源

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Joint Pose and Ex...

    Facial expression recognition (FER) is a challe...

  • Depth Super Resol...

    We tackle the problem of jointly increasing the...

  • The Variational S...

    Unlike traditional images which do not offer in...