Geodesic
Maximizing the Bregman divergence from a Bregman family
Kybernetika, Tome 56 (2020) no. 5, pp. 875-885
Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

The problem to maximize the information divergence from an exponential family is generalized to the setting of Bregman divergences and suitably defined Bregman families.
The problem to maximize the information divergence from an exponential family is generalized to the setting of Bregman divergences and suitably defined Bregman families.
DOI : 10.14736/kyb-2020-5-0875
Classification : 52A41, 62B05, 62E15, 62E17, 94A17
Keywords: Bregman divergence; relative entropy; exponential family; optimization 
@article{10_14736_kyb_2020_5_0875,
     author = {Rauh, Johannes and Mat\'u\v{s}, Franti\v{s}ek},
     title = {Maximizing the {Bregman} divergence from a {Bregman} family},
     journal = {Kybernetika},
     pages = {875--885},
     year = {2020},
     volume = {56},
     number = {5},
     doi = {10.14736/kyb-2020-5-0875},
     mrnumber = {4187777},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.14736/kyb-2020-5-0875/}
}
TY  - JOUR
AU  - Rauh, Johannes
AU  - Matúš, František
TI  - Maximizing the Bregman divergence from a Bregman family
JO  - Kybernetika
PY  - 2020
SP  - 875
EP  - 885
VL  - 56
IS  - 5
UR  - http://geodesic.mathdoc.fr/articles/10.14736/kyb-2020-5-0875/
DO  - 10.14736/kyb-2020-5-0875
LA  - en
ID  - 10_14736_kyb_2020_5_0875
ER  - 
%0 Journal Article
%A Rauh, Johannes
%A Matúš, František
%T Maximizing the Bregman divergence from a Bregman family
%J Kybernetika
%D 2020
%P 875-885
%V 56
%N 5
%U http://geodesic.mathdoc.fr/articles/10.14736/kyb-2020-5-0875/
%R 10.14736/kyb-2020-5-0875
%G en
%F 10_14736_kyb_2020_5_0875
Rauh, Johannes; Matúš, František. Maximizing the Bregman divergence from a Bregman family. Kybernetika, Tome 56 (2020) no. 5, pp. 875-885. doi: 10.14736/kyb-2020-5-0875

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

[2] Ay, N., Knauf, A.: Maximizing multi-information. Kybernetika 42 (2006), 517-538. | MR | Zbl

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

[4] Csiszár, I., Matúš, F.: Closures of exponential families. Ann. Probab. 33 (2005), 582-600. | DOI | MR | Zbl

[5] Csiszár, I., Matúš, F.: Generalized maximum likelihood extimates for exponential families. Probab. Theory Related Fields 141 (2008), 213-246. | DOI | MR

[6] Geiger, D., Meek, C., Sturmfels, B.: On the toric algebra of graphical models. Ann. Statist. 34 (2006), 1463-1492. | DOI | MR | Zbl

[7] Matúš, F.: Maximization of information divergences from binary i.i.d. sequences. In: Proc. IPMU 2 (2004), 1303-1306.

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

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

[10] Matúš, F., Ay, N.: On maximization of the information divergence from an exponential family. In: Proc. WUPES 2003, University of Economics, Prague 2003, pp. 199-204.

[11] Matúš, F., Csiszár, I.: Generalized minimizers of convex integral functionals, Bregman distance, Pythagorean identities. Kybernetika 48 (2012), 637-689. | MR

[12] Matúš, F., Rauh, J.: Maximization of the information divergence from an exponential family and criticality. In: Proc. IEEE International Symposium on Information Theory (ISIT2011), 2011. | DOI | MR

[13] Montúfar, G., Rauh, J., Ay, N.: Expressive power and approximation errors of Restricted Boltzmann Machines. In: Proc. NIPS 2011.

[14] Montúfar, G., Rauh, J., Ay, N.: Maximal information divergence from statistical models defined by neural networks. In: Proc. GSI, 2013, pp. 759-766. | DOI

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

[16] Rauh, J.: Finding the Maximizers of the Information Divergence from an Exponential Family. Ph.D. Dissertation, Universität Leipzig, 2011. | MR

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

[18] Wang, N., Rauh, J., Massam, H.: Approximating faces of marginal polytopes in discrete hierarchical models. Ann. Statist. 47 (2019), 1203-1233. | DOI | MR

Cité par Sources :