Tightening Mutual Information Based Bounds on Generalization Error

Yuheng Bu, Shaofeng Zou, Venugopal V. Veeravalli

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A mutual information based upper bound on the generalization error of a supervised learning algorithm is derived in this paper. The bound is constructed in terms of the mutual information between each individual training sample and the output of the learning algorithm, which requires weaker conditions on the loss function, but provides a tighter characterization of the generalization error than existing studies. Examples are further provided to demonstrate that the bound derived in this paper is tighter, and has a broader range of applicability. Application to noisy and iterative algorithms, e.g., stochastic gradient Langevin dynamics (SGLD), is also studied, where the constructed bound provides a tighter characterization of the generalization error than existing results.

Original languageEnglish (US)
Title of host publication2019 IEEE International Symposium on Information Theory, ISIT 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages587-591
Number of pages5
ISBN (Electronic)9781538692912
DOIs
StatePublished - Jul 2019
Event2019 IEEE International Symposium on Information Theory, ISIT 2019 - Paris, France
Duration: Jul 7 2019Jul 12 2019

Publication series

NameIEEE International Symposium on Information Theory - Proceedings
Volume2019-July
ISSN (Print)2157-8095

Conference

Conference2019 IEEE International Symposium on Information Theory, ISIT 2019
Country/TerritoryFrance
CityParis
Period7/7/197/12/19

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Information Systems
  • Modeling and Simulation
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Tightening Mutual Information Based Bounds on Generalization Error'. Together they form a unique fingerprint.

Cite this