A new metric for probability distributions

Dominik Maria Endres, J E Schindelin

Research output: Contribution to journalArticlepeer-review

540 Citations (Scopus)

Abstract

We introduce a metric for probability distributions, which is bounded, information-theoretically motivated, and has a natural Bayesian interpretation. The square root of the well-known chi(2) distance is an asymptotic approximation to it. Moreover, it is a close relative of the capacitory discrimination and Jensen-Shannon divergence.

Original languageEnglish
Pages (from-to)1858- 1860
Number of pages3
JournalIEEE Transactions on Information Theory
Volume49
Issue number7
DOIs
Publication statusPublished - Jul 2003

Keywords

  • Capacitory discrimination
  • Chi(2) distance
  • Jensen-Shannon divergence
  • Metric
  • Triangle inequality
  • Discrimination
  • Information
  • Divergence

Fingerprint

Dive into the research topics of 'A new metric for probability distributions'. Together they form a unique fingerprint.

Cite this