Article
Full entry |
PDF
(1.8 MB)
Feedback
PDF
(1.8 MB)
Feedback
Summary:
The asymptotic Rényi distances are explicitly defined and rigorously studied for a convenient class of Gibbs random fields, which are introduced as a natural infinite-dimensional generalization of exponential distributions.
References:
[1] Csiszár I.: Information–type measures of difference of probability distributions and indirect observations. Stud. Sci. Math. Hungar. 2 (1967), 299–318 MR 0219345 | Zbl 0157.25802
[2] Georgii H. O.: Gibbs Measures and Place Transitions. de Gruyter, Berlin 1988 MR 0956646
[3] Liese F., Vajda I.: Convex Statistical Problems. Teubner, Leipzig 1987 MR 0926905
[4] Perez A.: Risk estimates in terms of generalized $f$–entropies. In: Proc. Colloq. Inform. Theory (A. Rényi, ed.), Budapest 1968 MR 0263542
[5] Rényi A.: On measure of entropy and information. In: Proc. 4th Berkeley Symp. Math. Statist. Probab., Univ. of Calif. Press, Berkeley 1961, Vol. 1, pp. 547–561 MR 0132570
[6] Vajda I.: On the $f$–divergence and singularity of probability measures. Period. Math. Hungar. 2 (1972), 223–234 DOI 10.1007/BF02018663 | MR 0335163 | Zbl 0248.62001
[7] Vajda I.: The Theory of Statistical Inference and Information. Kluwer, Dordrecht – Boston – London 1989
Search
Partner of
