A new metric for probability distributions

Endres, Dominik; Schindelin, J.E.

doi:10.1109/tit.2003.813506

articleIEEE Transactions on Information TheoryJun 23, 2003GREEN OA

A new metric for probability distributions

DEDominik Endres JSJ.E. Schindelin

University of St Andrews · University of Würzburg

Indexed incrossref

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 /spl chi//sup 2/ distance is an asymptotic approximation to it. Moreover, it is a close relative of the capacitory discrimination and Jensen-Shannon divergence.

Citation impact

1,159

total citations

FWCI: 8.70
Percentile: 100%
References: 8

Citations per year

Authors

2

Topics & keywords

Topics

Keywords

Metric (unit)
Mathematics
Divergence (linguistics)
Probability distribution
Bounded function
Kullback–Leibler divergence
Statistical distance
Interpretation (philosophy)

UN Sustainable Development Goals

Reduced inequalities

No related works found for this paper.