On escort distributions, q-gaussians and Fisher information

被引:0
|
作者
Bercher, J. -F. [1 ]
机构
[1] Univ Paris Est, Lab Informat Gaspard Monge, ESIEE, F-77454 Marne La Vallee 2, France
关键词
nonextensive theory; escort distributions; Renyi-Tsallis entropy; Fisher information;
D O I
暂无
中图分类号
O414.1 [热力学];
学科分类号
摘要
Escort distributions are a simple one parameter deformation of an original distribution p. In Tsallis extended thermostatistics, the escort-averages, defined with respect to an escort distribution, have revealed useful in order to obtain analytical results and variational equations, with in particular the equilibrium distributions obtained as maxima of Renyi-Tsallis entropy subject to constraints in the form of a q-average. A central example is the q-gaussian, which is a generalization of the standard gaussian distribution. In this contribution, we show that escort distributions emerge naturally as a maximum entropy trade-off between the distribution p(x) and the uniform distribution. This setting may typically describe a phase transition between two states. But escort distributions also appear in the fields of multifractal analysis, quantization and coding with interesting consequences. For the problem of coding, we recall a source coding theorem by Campbell relating a generalized measure of length to the Renyi-Tsallis entropy and exhibit the links with escort distributions together with pratical implications. That q-gaussians arise from the maximization of Renyi-Tsallis entropy subject to a q-variance constraint is a known fact. We show here that the (squared) q-gaussian also appear as a minimum of Fisher information subject to the same q-variance constraint.
引用
收藏
页码:208 / 215
页数:8
相关论文
共 50 条
  • [31] On generalized Cramer-Rao inequalities, generalized Fisher information and characterizations of generalized q-Gaussian distributions
    Bercher, J-F
    JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL, 2012, 45 (25)
  • [32] Fisher information, Borges operators, and q-calculus
    Pennini, F.
    Plastino, A.
    Ferri, G. L.
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2008, 387 (23) : 5778 - 5785
  • [33] Discrete Versions of Jensen-Fisher, Fisher and Bayes-Fisher Information Measures of Finite Mixture Distributions
    Kharazmi, Omid
    Balakrishnan, Narayanaswamy
    ENTROPY, 2021, 23 (03)
  • [34] Power-law distributions and Fisher's information measure
    Pennini, F
    Plastino, A
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2004, 334 (1-2) : 132 - 138
  • [35] On the Fisher-Rao Information Metric in the Space of Normal Distributions
    Pinele, Julianna
    Costa, Sueli I. R.
    Strapasson, Joao E.
    GEOMETRIC SCIENCE OF INFORMATION, 2019, 11712 : 676 - 684
  • [36] FISHER INFORMATION AND STATISTICAL INFERENCE FOR PHASE-TYPE DISTRIBUTIONS
    Bladt, Mogens
    Esparza, Luz Judith R.
    Nielsen, Bo Friis
    JOURNAL OF APPLIED PROBABILITY, 2011, 48A : 277 - 293
  • [37] On the characterization of fisher information and stability of the least favorable lattice distributions
    Vil'chevskii N.O.
    Shevlyakov G.L.
    Journal of Mathematical Sciences, 1998, 92 (4) : 4104 - 4111
  • [38] On minimum Fisher information distributions with restricted support and fixed variance
    Bercher, J. -F.
    Vignat, C.
    INFORMATION SCIENCES, 2009, 179 (22) : 3832 - 3842
  • [39] Shrinkage Fisher Information Embedding of High Dimensional Feature Distributions
    Chen, Xu
    Chen, Yilun
    Hero, Alfred
    2011 CONFERENCE RECORD OF THE FORTY-FIFTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS (ASILOMAR), 2011, : 1877 - 1882
  • [40] Clustering Financial Return Distributions Using the Fisher Information Metric
    Taylor, Stephen
    ENTROPY, 2019, 21 (02):