DIM: Learning Deep Representations by Mutual Information Estimation and Maximization

This is our second article of the series about mutual information. In the previous articles, we have seen how to maximizes the mutual information between two variables via the MINE estimator and some practical applications of maximizing mutual information. In this article, we focus on representation learning with mutual information maximization. Specifically, we will discuss an adversarial architecture for representation learning and two other objectives of mutual information maximization that has been experimentally shown to outperform MINE estimator for downstream tasks. This article is organized into four parts.