GILBO: One Metric to Measure Them All
arXiv:1802.04874
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.
arXiv commentAccepted at NeurIPS 2018
References in corpus (9)
- Auto-Encoding Variational Bayes
- Representation Learning with Contrastive Predictive Coding
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Validating Bayesian Inference Algorithms with Simulation-Based Calibration
- Do GANs actually learn the distribution? An empirical study
- Estimating Mutual Information for Discrete-Continuous Mixtures
- Comparison of Maximum Likelihood and GAN-based training of Real NVPs
- Fixing a Broken ELBO
- On the Quantitative Analysis of Decoder-Based Generative Models