UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Tighter Expected Generalization Error Bounds via Convexity of Information Measures

Aminian, Gholamali; Bu, Yuheng; Wornell, Gregory W; Rodrigues, Miguel RD; (2022) Tighter Expected Generalization Error Bounds via Convexity of Information Measures. In: Proceedings of the IEEE International Symposium on Information Theory (ISIT) 2022. (pp. pp. 2481-2486). Institute of Electrical and Electronics Engineers (IEEE) Green open access

[thumbnail of 2202.12150.pdf]
Preview
Text
2202.12150.pdf - Accepted Version

Download (244kB) | Preview

Abstract

Generalization error bounds are essential to understanding machine learning algorithms. This paper presents novel expected generalization error upper bounds based on the average joint distribution between the output hypothesis and each input training sample. Multiple generalization error upper bounds based on different information measures are provided, including Wasserstein distance, total variation distance, KL divergence, and Jensen-Shannon divergence. Due to the convexity of the information measures, the proposed bounds in terms of Wasserstein distance and total variation distance are shown to be tighter than their counterparts based on individual samples in the literature. An example is provided to demonstrate the tightness of the proposed generalization error bounds.

Type: Proceedings paper
Title: Tighter Expected Generalization Error Bounds via Convexity of Information Measures
Event: 2022 IEEE International Symposium on Information Theory (ISIT)
Location: Espoo, Finland
Dates: 26th June - 1st July 2022
ISBN-13: 978-1-6654-2159-1
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/isit50566.2022.9834474
Publisher version: https://doi.org/10.1109/ISIT50566.2022.9834474
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.
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/10175497
Downloads since deposit
Loading...
20Downloads
Download activity - last month
Loading...
Download activity - last 12 months
Loading...
Downloads by country - last 12 months
Loading...

Archive Staff Only

View Item View Item