Timezone: »
Poster
Meta-Gaussian Information Bottleneck
Melanie Rey · Volker Roth
Mon Dec 03 07:00 PM -- 12:00 AM (PST) @ Harrah’s Special Events Center 2nd Floor
We present a reformulation of the information bottleneck (IB) problem in terms of copula, using the equivalence between mutual information and negative copula entropy. Focusing on the Gaussian copula we extend the analytical IB solution available for the multivariate Gaussian case to distributions with a Gaussian dependence structure but arbitrary marginal densities, also called meta-Gaussian distributions. This opens new possibles applications of IB to continuous data and provides a solution more robust to outliers.
Author Information
Melanie Rey (DeepMind)
Volker Roth (University of Basel)
More from the Same Authors
-
2021 : Gaussian dropout as an information bottleneck layer »
Melanie Rey · Andriy Mnih -
2020 Poster: Inverse Learning of Symmetries »
Mario Wieser · Sonali Parbhoo · Aleksander Wieczorek · Volker Roth -
2014 Poster: Distance-Based Network Recovery under Feature Correlation »
David Adametz · Volker Roth -
2011 Poster: Bayesian Partitioning of Large-Scale Distance Data »
David Adametz · Volker Roth