Research Area:  Machine Learning
We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutual Information Neural Estimator (MINE) that is linearly scalable in dimensionality as well as in sample size, trainable through back-prop, and strongly consistent. We present a handful of applications on which MINE can be used to minimize or maximize mutual information. We apply MINE to improve adversarially trained generative models. We also use MINE to implement the Information Bottleneck, applying it to supervised classification; our results demonstrate substantial improvement in flexibility and performance in these settings.
Keywords:  
Mutual Information Neural Estimation
Machine Learning
Deep Learning
Author(s) Name:  Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeshwar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, Devon Hjelm
Journal name:  
Conferrence name:  Proceedings of the 35th International Conference on Machine Learning
Publisher name:  PMLR
DOI:  
Volume Information:  PMLR 80:531-540
Paper Link:   https://proceedings.mlr.press/v80/belghazi18a.html