Previous |  Up |  Next

Article

Title: Generalized information criteria for Bayes decisions (English)
Author: Morales, Domingo
Author: Vajda, Igor
Language: English
Journal: Kybernetika
ISSN: 0023-5954
Volume: 48
Issue: 4
Year: 2012
Pages: 714-749
Summary lang: English
.
Category: math
.
Summary: This paper deals with Bayesian models given by statistical experiments and standard loss functions. Bayes probability of error and Bayes risk are estimated by means of classical and generalized information criteria applicable to the experiment. The accuracy of the estimation is studied. Among the information criteria studied in the paper is the class of posterior power entropies which include the Shannon entropy as special case for the power $\alpha =1$. It is shown that the most accurate estimate is in this class achieved by the quadratic posterior entropy of the power $\alpha =2$. The paper introduces and studies also a new class of alternative power entropies which in general estimate the Bayes errors and risk more tightly than the classical power entropies. Concrete examples, tables and figures illustrate the obtained results. (English)
Keyword: Shannon entropy
Keyword: alternative Shannon entropy
Keyword: power entropies
Keyword: alternative power entropies
Keyword: Bayes error
Keyword: Bayes risk
Keyword: sub-Bayes risk
MSC: 62B10
MSC: 62C10
idMR: MR3013396
.
Date available: 2012-11-10T22:04:58Z
Last updated: 2013-09-24
Stable URL: http://hdl.handle.net/10338.dmlcz/143057
.
Reference: [1] M. Ben Bassat: $f$-entropies, probability of error, and feature selection..Inform. Control 39 (1978), 227-242. Zbl 0394.94011, MR 0523439, 10.1016/S0019-9958(78)90587-9
Reference: [2] M. Ben Bassat, J. Raviv: Rényi's entropy and probability of error..IEEE Trans. Inform. Theory 24 (1978), 324-331. MR 0484747, 10.1109/TIT.1978.1055890
Reference: [3] J. O. Berger: Statistical Decision Theory and Bayesian Analysis. Second edition..Springer, Berlin 1986. MR 0804611
Reference: [4] T. M. Cover, P. E. Hart: Nearest neighbor pattern classification..IEEE Trans. Inform. Theory 13 (1967), 21-27. Zbl 0154.44505, 10.1109/TIT.1967.1053964
Reference: [5] P. Devijver, J. Kittler: Pattern Recognition. A Statistical Approach..Prentice Hall, Englewood Cliffs, New Jersey 1982. Zbl 0542.68071, MR 0692767
Reference: [6] L. Devroye, L. Györfi, G. Lugosi: A Probabilistic Theory of Pattern Recognition 1996..Springer, Berlin 1996. MR 1383093
Reference: [7] D. K. Faddeev: Zum Begriff der Entropie einer endlichen Wahrscheinlichkeitsschemas..Vol. I. Deutscher Verlag der Wissenschaften, Berlin 1957.
Reference: [8] M. Feder, N. Merhav: Relations between entropy and error probability..IEEE Trans. Inform. Theory 40 (1994), 259-266. Zbl 0802.94004, 10.1109/18.272494
Reference: [9] P. Harremoës, F. Topsøe: Inequalities between entropy and index of coincidence derived from information diagrams..IEEE Trans. Inform. Theory 47 (2001), 2944-2960. MR 1872852, 10.1109/18.959272
Reference: [10] J. Havrda, F. Charvát: Concept of structural $a$-entropy..Kybernetika 3 (1967), 30-35. Zbl 0178.22401, MR 0209067
Reference: [11] L. Kanal: Patterns in pattern recognittion..IEEE Trans. Inform. Theory 20 (1974), 697-707. MR 0356609
Reference: [12] V. A. Kovalevsky: The problem of character recognition from the point of view of mathematical statistics..In: Reading Automata and Pattern Recognition (in Russian) (Naukova Dumka, Kyjev, ed. 1965). English translation in: Character Readers and Pattern Recognition, Spartan Books, New York 1968, pp. 3-30.
Reference: [13] D. Morales, L. Pardo, I. Vajda: Uncertainty of discrete stochastic systems: general theory and statistical inference..IEEE Trans. System, Man and Cybernetics, Part A 26 (1996), 1-17.
Reference: [14] A. Rényi: Proceedings of 4th Berkeley Symp. on Probab. Statist..University of California Press, Berkeley, California 1961. MR 0132570
Reference: [15] N. P. Salikhov: Confirmation of a hypothesis of I. Vajda (in Russian)..Problemy Peredachi Informatsii 10 (1974), 114-115. MR 0464476
Reference: [16] D. L. Tebbe, S. J. Dwyer III: Uncertainty and probability of error..IEEE Trans. Inform. Theory 14 (1968), 516-518. 10.1109/TIT.1968.1054135
Reference: [17] G. T. Toussaint: A generalization of Shannon's equivocation and the Fano bound..IEEE Trans. System, Man and Cybernetics 7 (1977), 300-302. Zbl 0363.94024, MR 0453269, 10.1109/TSMC.1977.4309705
Reference: [18] I. Vajda: Bounds on the minimal error probability and checking a finite or countable number of hypotheses..Inform. Transmission Problems 4 (1968), 9-17. MR 0267685
Reference: [19] I. Vajda: A contribution to informational analysis of patterns..In: Methodologies of Pattern Recognition (M. S. Watanabe, ed.), Academic Press, New York 1969.
Reference: [20] I. Vajda, K. Vašek: Majorization, concave entropies and comparison of experiments..Problems Control Inform. Theory 14 (1985), 105-115. Zbl 0601.62006, MR 0806056
Reference: [21] I. Vajda, J. Zvárová: On generalized entropies, Bayesian decisions and statistical diversity..Kybernetika 43 (2007), 675-696. Zbl 1143.94006, MR 2376331
.

Files

Files Size Format View
Kybernetika_48-2012-4_6.pdf 523.2Kb application/pdf View/Open
Back to standard record
Partner of
EuDML logo