THE REPRESENTATION JENSEN-RÉNYI DIVERGENCE

Jhoan Keider Hoyos Osorio, Oscar Skean, Austin J. Brockmeier, Luis Gonzalo Sanchez Giraldo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We introduce a divergence measure between data distributions based on operators in reproducing kernel Hilbert spaces defined by kernels. The empirical estimator of the divergence is computed using the eigenvalues of positive definite Gram matrices that are obtained by evaluating the kernel over pairs of data points. The new measure shares similar properties to Jensen-Shannon divergence. Convergence of the proposed estimators follows from concentration results based on the difference between the ordered spectrum of the Gram matrices and the integral operators associated with the population quantities. The proposed measure of divergence avoids the estimation of the probability distribution underlying the data. Numerical experiments involving comparing distributions and applications to sampling unbalanced data for classification show that the proposed divergence can achieve state of the art results.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
Pages4313-4317
Number of pages5
ISBN (Electronic)9781665405409
DOIs
StatePublished - 2022
Event47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore
Duration: May 23 2022May 27 2022

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityVirtual, Online
Period5/23/225/27/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE

Keywords

  • Divergence
  • Imbalanced classification
  • Information theoretic learning
  • Kernel methods
  • Subsampling

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'THE REPRESENTATION JENSEN-RÉNYI DIVERGENCE'. Together they form a unique fingerprint.

Cite this