A NEW DIRECTED DIVERGENCE MEASURE AND ITS CHARACTERIZATION∗
- 1 May 1990
- journal article
- research article
- Published by Taylor & Francis in International Journal of General Systems
- Vol. 17 (1) , 73-81
- https://doi.org/10.1080/03081079008935097
Abstract
A new information-theoretic divergence measure is introduced and characterized. This new measure is related to the Kullback directed divergence but does not require the condition of absolute continuity to be satisfied by the probability distributions involved. Moreover, both the lower and upper bounds for the new measure are established in terms of the variational distance. A symmetric form of the divergence can also be defined and described by the Shannon entropy function. Other properties of the new divergences: nonnegativity, finiteness, semiboundedness, and boundedness are discussedKeywords
This publication has 12 references indexed in Scilit:
- SOME NORMALIZED MEASURES OF DIRECTED DIVERGENCEInternational Journal of General Systems, 1986
- Cross entropy, dissimilarity measures, and characterizations of quadratic entropyIEEE Transactions on Information Theory, 1985
- Diversity and dissimilarity coefficients: A unified approachTheoretical Population Biology, 1982
- A Decision Theory Approach to the Approximation of Discrete Probability DensitiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1980
- Sharper lower bounds for discrimination information in terms of variation (Corresp.)IEEE Transactions on Information Theory, 1975
- Note on discrimination information and variation (Corresp.)IEEE Transactions on Information Theory, 1970
- Approximating discrete probability distributions with dependence treesIEEE Transactions on Information Theory, 1968
- On the best finite set of linear observables for discriminating two Gaussian signalsIEEE Transactions on Information Theory, 1967
- A lower bound for discrimination information in terms of variation (Corresp.)IEEE Transactions on Information Theory, 1967
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951