We propose a novel approach to the problem of mutual information (MI) estimation via
introducing normalizing flows-based estimator. The estimator maps original data to the …

Estimating mutual information is an important statistics and machine learning problem. To
estimate the mutual information from data, a common practice is preparing a set of paired …

Learning representations in an unsupervised or self-supervised manner is a growing area of
research. Current approaches in representation learning seek to maximize the mutual …

We introduce a mutual information estimator based on the connection between estimation
theory and information theory. By combining a polynomial approximation of the minimum …

Abstract Mutual information I (X; Y) is a useful definition in information theory to estimate how
much information the random variable Y holds about the random variable X. One way to …

We propose a new method of approximating mutual information based on maximum
likelihood estimation of a density ratio function. The proposed method, Maximum Likelihood …

Mutual information (MI) quantifies the statistical dependency between a pair of random
variables, and plays a central role in the analysis of engineering and biological systems …

The estimation of mutual information (MI) or conditional mutual information (CMI) from a set
of samples is a longstanding problem. A recent line of work in this area has leveraged the …

We derive the mean squared error convergence rates of kernel density-based plug-in
estimators of mutual information measures between two multidimensional random variables …

Mutual information is a measure of the dependence between random variables that has
been used successfully in myriad applications in many fields. Generalized mutual …