DiME: Maximizing Mutual Information by a Difference of Matrix-Based Entropies

1 code implementation • 19 Jan 2023 • Oscar Skean, Jhoan Keider Hoyos Osorio, Austin J. Brockmeier, Luis Gonzalo Sanchez Giraldo

We introduce an information-theoretic quantity with similar properties to mutual information that can be estimated from data without making explicit assumptions on the underlying distribution.

Disentanglement Mutual Information Estimation

The Representation Jensen-Rényi Divergence

1 code implementation • 2 Dec 2021 • Jhoan Keider Hoyos Osorio, Oscar Skean, Austin J. Brockmeier, Luis Gonzalo Sanchez Giraldo

We introduce a divergence measure between data distributions based on operators in reproducing kernel Hilbert spaces defined by kernels.