To estimate mutual information from samples, specially for high-dimensional variables.
The estimation of an f-divergence between two probability distributions based on samples is a fundamental problem in statistics and machine learning.
In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder.
However, many of the state of the art deep reinforcement learning algorithms, that rely on epsilon-greedy, fail on these environments.
The richness in the content of various information networks such as social networks and communication networks provides the unprecedented potential for learning high-quality expressive representations without external supervision.
To the best of our knowledge EDGE is the first non-parametric MI estimator that can achieve parametric MSE rates with linear time complexity.
In particular, we show that MI-NEE reduces to MINE in the special case when the reference distribution is the product of marginal distributions, but faster convergence is possible by choosing the uniform distribution as the reference distribution instead.
In this work, we develop a novel regularizer to improve the learning of long-range dependency of sequence data.
We provide numerical experiments suggesting superiority of the proposed estimator compared to other heuristics of adding small continuous noise to all the samples and applying standard estimators tailored for purely continuous variables, and quantizing the samples and applying standard estimators tailored for purely discrete variables.