On limiting towards the boundaries of exponential families
Kybernetika, Tome 51 (2015) no. 5, pp. 725-738
Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

This work studies the standard exponential families of probability measures on Euclidean spaces that have finite supports. In such a family parameterized by means, the mean is supposed to move along a segment inside the convex support towards an endpoint on the boundary of the support. Limit behavior of several quantities related to the exponential family is described explicitly. In particular, the variance functions and information divergences are studied around the boundary.
This work studies the standard exponential families of probability measures on Euclidean spaces that have finite supports. In such a family parameterized by means, the mean is supposed to move along a segment inside the convex support towards an endpoint on the boundary of the support. Limit behavior of several quantities related to the exponential family is described explicitly. In particular, the variance functions and information divergences are studied around the boundary.
DOI : 10.14736/kyb-2015-5-0725
Classification : 60A10, 62B10, 94A17
Keywords: exponential family; variance function; Kullback–Leibler divergence; relative entropy; information divergence; mean parametrization; convex support
@article{10_14736_kyb_2015_5_0725,
     author = {Mat\'u\v{s}, Franti\v{s}ek},
     title = {On limiting towards the boundaries of exponential families},
     journal = {Kybernetika},
     pages = {725--738},
     year = {2015},
     volume = {51},
     number = {5},
     doi = {10.14736/kyb-2015-5-0725},
     mrnumber = {3445980},
     zbl = {06537776},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.14736/kyb-2015-5-0725/}
}
TY  - JOUR
AU  - Matúš, František
TI  - On limiting towards the boundaries of exponential families
JO  - Kybernetika
PY  - 2015
SP  - 725
EP  - 738
VL  - 51
IS  - 5
UR  - http://geodesic.mathdoc.fr/articles/10.14736/kyb-2015-5-0725/
DO  - 10.14736/kyb-2015-5-0725
LA  - en
ID  - 10_14736_kyb_2015_5_0725
ER  - 
%0 Journal Article
%A Matúš, František
%T On limiting towards the boundaries of exponential families
%J Kybernetika
%D 2015
%P 725-738
%V 51
%N 5
%U http://geodesic.mathdoc.fr/articles/10.14736/kyb-2015-5-0725/
%R 10.14736/kyb-2015-5-0725
%G en
%F 10_14736_kyb_2015_5_0725
Matúš, František. On limiting towards the boundaries of exponential families. Kybernetika, Tome 51 (2015) no. 5, pp. 725-738. doi: 10.14736/kyb-2015-5-0725

[1] Ay, N.: An information-geometric approach to a theory of pragmatic structuring. The Annals of Probability 30 (2002), 416-436. | DOI | MR | Zbl

[2] Barndorff-Nielsen, O.: Information and Exponential Families in Statistical Theory. Wiley, New York 1978. | MR | Zbl

[3] Brown, L. D.: Fundamentals of Statistical Exponential Families. Inst. of Math. Statist. Lecture Notes - Monograph Series 9 (1986). | MR | Zbl

[4] Chentsov, N. N.: Statistical Decision Rules and Optimal Inference. Translations of Mathematical Monographs, Amer. Math. Soc., Providence - Rhode Island 1982 (Russian original: Nauka, Moscow, 1972). | MR | Zbl

[5] Csiszár, I., Matúš, F.: Closures of exponential families. The Annals of Probability 33 (2005), 582-600. | DOI | MR | Zbl

[6] Csiszár, I., Matúš, F.: Generalized maximum likelihood estimates for exponential families. Probability Theory and Related Fields 141 (2008), 213-246. | DOI | MR | Zbl

[7] Graham, R., Knuth, D., Patashnik, O.: Concrete Mathematics. Second edition. Addison-Wesley, Reading, Massachusetts 1994, p. 446. | MR

[8] Letac, G.: Lectures on Natural Exponential Families and their Variance Functions. Monografias de Matemática 50, Instituto de Matemática Pura e Aplicada, Rio de Janeiro 1992. | MR | Zbl

[9] Matúš, F., Ay, N.: On maximization of the information divergence from an exponential family. In: Proc. WUPES'03 (J. Vejnarová, ed.), University of Economics, Prague 2003, pp. 99-204.

[10] Matúš, F.: Optimality conditions for maximizers of the divergence from an EF. Kybernetika 43 (2007), 731-746. | MR

[11] Matúš, F.: Divergence from factorizable distributions and matroid representations by partitions. IEEE Trans. Inform. Theory 55 (2009), 5375-5381. | DOI | MR

[12] F., F.Matúš, Rauh, J.: Maximization of the information divergence from an exponential family and criticality. In: Proc. IEEE ISIT 2011, St. Petersburg 2011, pp. 809-813. | DOI

[13] Montúfar, G., J., J. Rauh, Ay, N.: Maximal information divergence from statistical models defined by neural networks. In: Proc. GSI 2013, Paris 2013, Lecture Notes in Computer Science 8085 (2013), 759-766. | DOI | Zbl

[14] Rauh, J.: Finding the maximizers of the information divergence from an exponential family. IEEE Trans. Inform. Theory 57 (2011), 3236-3247. | DOI | MR

[15] Rockafellar, R. T.: Convex Analysis. Princeton University Press, 1970. | DOI | MR | Zbl

Cité par Sources :