2018
NIPS
NeurIPS 2018
GILBO: One Metric to Measure Them All
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.
🌱
Topic Pioneer
— Representation Learning
🌉
Interdisciplinary Bridge
— Artificial Intelligence and Deep Learning and Machine Learning
🧭
Keyword Pioneer
— information lower bound
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
Authors
Topics
Machine Learning > Core Methods > Representation Learning
Deep Learning > Models > Generative Models
Deep Learning > Models > Variational Inference
Machine Learning > Optimization & Theory > Information Theory
Machine Learning > Learning Types > Representation Learning
Artificial Intelligence > Core AI > Representation Learning