Aminian, G;
Toni, L;
Rodrigues, M;
(2021)
Jensen-Shannon Information Based Characterization of the Generalization Error of Learning Algorithms.
In:
Proceedings of the 2020 IEEE Information Theory Workshop (ITW).
IEEE: Riva del Garda, Italy.
Preview |
Text
ITW_Jensen_Shannon_Upper_Bound-4.pdf - Accepted Version Download (307kB) | Preview |
Abstract
Generalization error bounds are critical to understanding the performance of machine learning models. In this work, we propose a new information-theoretic based generalization error upper bound applicable to supervised learning scenarios. We show that our general bound can specialize in various previous bounds. We also show that our general bound can be specialized under some conditions to a new bound involving the Jensen-Shannon information between a random variable modelling the set of training samples and another random variable modelling the hypothesis. We also prove that our bound can be tighter than mutual information-based bounds under some conditions.
| Type: | Proceedings paper |
|---|---|
| Title: | Jensen-Shannon Information Based Characterization of the Generalization Error of Learning Algorithms |
| Event: | 2020 IEEE Information Theory Workshop (ITW) |
| Dates: | 11 April 2021 - 15 April 2021 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/ITW46852.2021.9457642 |
| Publisher version: | https://doi.org/10.1109/ITW46852.2021.9457642 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Generalization Error Bounds, Mutual Information, Jensen-Shannon Information |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10118789 |
Archive Staff Only
 |
View Item |
