Previous |  Up |  Next

Article

Title: Optimally approximating exponential families (English)
Author: Rauh, Johannes
Language: English
Journal: Kybernetika
ISSN: 0023-5954 (print)
ISSN: 1805-949X (online)
Volume: 49
Issue: 2
Year: 2013
Pages: 199-215
Summary lang: English
.
Category: math
.
Summary: This article studies exponential families $\mathcal{E}$ on finite sets such that the information divergence $D(P\|\mathcal{E})$ of an arbitrary probability distribution from $\mathcal{E}$ is bounded by some constant $D>0$. A particular class of low-dimensional exponential families that have low values of $D$ can be obtained from partitions of the state space. The main results concern optimality properties of these partition exponential families. The case where $D=\log(2)$ is studied in detail. This case is special, because if $D<\log(2)$, then $\mathcal{E}$ contains all probability measures with full support. (English)
Keyword: exponential family
Keyword: information divergence
MSC: 62B10
MSC: 94A15
MSC: 94A17
idZBL: Zbl 06176033
idMR: MR3085392
.
Date available: 2013-07-22T08:42:51Z
Last updated: 2016-01-03
Stable URL: http://hdl.handle.net/10338.dmlcz/143362
.
Reference: [1] Ay, N.: An information-geometric approach to a theory of pragmatic structuring..Ann. Probab. 30 (2002), 416-436. Zbl 1010.62007, MR 1894113, 10.1214/aop/1020107773
Reference: [2] Ay, N.: Locality of global stochastic interaction in directed acyclic networks..Neural Computat. 14 (2002), 2959-2980. Zbl 1079.68582, 10.1162/089976602760805368
Reference: [3] Brown, L.: Fundamentals of Statistical Exponential Families: With Applications in Statistical Decision Theory..Institute of Mathematical Statistics, Hayworth 1986. Zbl 0685.62002, MR 0882001
Reference: [4] Cover, T., Thomas, J.: Elements of Information Theory. First edition..Wiley, 1991. MR 1122806
Reference: [5] Csiszár, I., Shields, P.: Information Theory and Statistics: A Tutorial. First edition..Foundations and Trends in Communications and Information Theory. Now Publishers, 2004.
Reference: [6] Csiszár, I., Matúš, F.: Generalized maximum likelihood extimates for exponential families..Probab. Theory Rel. Fields 141 (2008), 213-246. MR 2372970, 10.1007/s00440-007-0084-z
Reference: [7] Pietra, S. Della, Pietra, V. Della, Lafferty, J.: Inducing features of random fields..IEEE Trans. Pattern Analysis and Machine Intelligence 19 (1997), 380-393. 10.1109/34.588021
Reference: [8] Drton, M., Sturmfels, B., Sullivant, S.: Lectures on algebraic statistics..In: Oberwolfach Seminars 39, Birkhäuser, Basel 2009. Zbl 1166.13001, MR 2723140
Reference: [9] Geiger, D., Meek, C., Sturmfels, B.: On the toric algebra of graphical models..Ann. Statist. 34 (2006), 5, 1463-1492. Zbl 1104.60007, MR 2278364, 10.1214/009053606000000263
Reference: [10] Jaynes, E. T.: Information theory and statistical mechanics..Phys. Rev. 106 (1957), 4, 620-630. Zbl 0084.43701, MR 0087305, 10.1103/PhysRev.106.620
Reference: [11] Juríček, J.: Maximization of information divergence from multinomial distributions..Acta Univ. Carolin. 52 (2011), 1, 27-35. MR 2808291
Reference: [12] Lauritzen, S. L.: Graphical Models. First edition..Oxford Statistical Science Series, Oxford University Press, 1996. MR 1419991
Reference: [13] Linsker, R.: Self-organization in a perceptual network..IEEE Computer 21 (1988), 105-117. 10.1109/2.36
Reference: [14] Matúš, F., Ay, N.: On maximization of the information divergence from an exponential family..In: Proc. WUPES'03, University of Economics, Prague 2003, pp. 199-204.
Reference: [15] Matúš, F., Rauh, J.: Maximization of the information divergence from an exponential family and criticality..In: 2011 IEEE International Symposium on Information Theory Proceedings (ISIT2011), 2011.
Reference: [16] Montúfar, G., Rauh, J., Ay, N.: Expressive power and approximation errors of Restricted Boltzmann Machines..In: NIPS, 2011.
Reference: [17] Oxley, J.: Matroid Theory. First edition..Oxford University Press, New York 1992. MR 1207587
Reference: [18] Rauh, J.: Finding the Maximizers of the Information Divergence from an Exponential Family..Ph.D. Dissertation, Universität Leipzig, 2011. MR 2817016
Reference: [19] Rauh, J.: Finding the maximizers of the information divergence from an exponential family..IEEE Trans. Inform. Theory 57 (2011), 6, 3236-3247. MR 2817016, 10.1109/TIT.2011.2136230
Reference: [20] Rauh, J., Kahle, T., Ay, N.: Support sets of exponential families and oriented matroids..Internat. J. Approx. Reasoning 52 (2011), 5, 613-626. MR 2787021, 10.1016/j.ijar.2011.01.013
Reference: [21] Zhu, S. C., Wu, Y. N., Mumford, D.: Minimax entropy principle and its application to texture modeling..Neural Computation 9 (1997), 1627-1660. 10.1162/neco.1997.9.8.1627
.

Files

Files Size Format View
Kybernetika_49-2013-2_1.pdf 374.8Kb application/pdf View/Open
Back to standard record
Partner of
EuDML logo