Geodesic
Information-type divergence when the likelihood ratios are bounded
Applicationes Mathematicae, Tome 24 (1997) no. 4, pp. 415-423 Cet article a éte moissonné depuis la source Institute of Mathematics Polish Academy of Sciences

Voir la notice de l'article

The so-called ϕ-divergence is an important characteristic describing "dissimilarity" of two probability distributions. Many traditional measures of separation used in mathematical statistics and information theory, some of which are mentioned in the note, correspond to particular choices of this divergence. An upper bound on a ϕ-divergence between two probability distributions is derived when the likelihood ratio is bounded. The usefulness of this sharp bound is illustrated by several examples of familiar ϕ-divergences. An extension of this inequality to ϕ-divergences between a finite number of probability distributions with pairwise bounded likelihood ratios is also given.
DOI : 10.4064/am-24-4-415-423
Keywords: information measures, multiple decisions, convexity, likelihood ratio

Andrew Rukhin 1

1 
@article{10_4064_am_24_4_415_423,
     author = {Andrew Rukhin},
     title = {Information-type divergence when the likelihood ratios are bounded},
     journal = {Applicationes Mathematicae},
     pages = {415--423},
     year = {1997},
     volume = {24},
     number = {4},
     doi = {10.4064/am-24-4-415-423},
     zbl = {0893.60008},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.4064/am-24-4-415-423/}
}
TY  - JOUR
AU  - Andrew Rukhin
TI  - Information-type divergence when the likelihood ratios are bounded
JO  - Applicationes Mathematicae
PY  - 1997
SP  - 415
EP  - 423
VL  - 24
IS  - 4
UR  - http://geodesic.mathdoc.fr/articles/10.4064/am-24-4-415-423/
DO  - 10.4064/am-24-4-415-423
LA  - en
ID  - 10_4064_am_24_4_415_423
ER  - 
%0 Journal Article
%A Andrew Rukhin
%T Information-type divergence when the likelihood ratios are bounded
%J Applicationes Mathematicae
%D 1997
%P 415-423
%V 24
%N 4
%U http://geodesic.mathdoc.fr/articles/10.4064/am-24-4-415-423/
%R 10.4064/am-24-4-415-423
%G en
%F 10_4064_am_24_4_415_423
Andrew Rukhin. Information-type divergence when the likelihood ratios are bounded. Applicationes Mathematicae, Tome 24 (1997) no. 4, pp. 415-423. doi: 10.4064/am-24-4-415-423

Cité par Sources :