Technical Program

Paper Detail

Paper IDL.10.2
Paper Title Robust Generalization via f-Mutual Information
Authors Amedeo Roberto Esposito, Michael Gastpar, EPFL, Switzerland; Ibrahim Issa, American University of Beirut, Lebanon
Session L.10: Learning Theory I
Presentation Lecture
Track Statistics and Learning Theory
Manuscript  Click here to download the manuscript
Virtual Presentation  Click here to watch in the Virtual Symposium
Abstract Given two probability measures $P$ and $Q$ and an event $E$, we provide bounds on $P(E)$ in terms of $Q(E)$ and $f-$divergences. In particular, the bounds are instantiated when the measures considered are a joint distribution and the corresponding product of marginals. This allows us to control the measure of an event under the joint, using the product of the marginals (typically easier to compute) and a measure of how much the two distributions differ, \textit{i.e.,} an $f-$divergence between the joint and the product of the marginals, also known in the literature as $f-$Mutual Information. The result is general enough to induce, as special cases, bounds involving $\chi^2$-divergence, Hellinger distance, Total Variation, etc. Moreover, it also recovers a result involving R\'enyi's $\alpha-$divergence. As an application, we provide bounds on the generalization error of learning algorithms via $f-$divergences.

Plan Ahead


2021 IEEE International Symposium on Information Theory

11-16 July 2021 | Melbourne, Victoria, Australia

Visit Website!