Next Article in Journal
On the Thermodynamics of Classical Micro-Canonical Systems
Next Article in Special Issue
Kullback–Leibler Divergence Measure for Multivariate Skew-Normal Distributions
Previous Article in Journal
EA/G-GA for Single Machine Scheduling Problems with Earliness/Tardiness Costs
Previous Article in Special Issue
Distances in Probability Space and the Statistical Complexity Setup
Open AccessArticle

Geometry of q-Exponential Family of Probability Distributions

by 1,* and 2,*
1
Laboratory for Mathematical Neuroscience, RIKEN Brain Science Institute, Hirosawa 2-1, Wako-shi, Saitama 351-0198, Japan
2
Department of Electrical and Electronics Engineering, Graduate School of Engineering, University of Fukui, Bunkyo 3-9-1, Fukui-shi, Fukui 910-8507, Japan
*
Authors to whom correspondence should be addressed.
Entropy 2011, 13(6), 1170-1185; https://doi.org/10.3390/e13061170
Received: 11 February 2011 / Revised: 1 June 2011 / Accepted: 2 June 2011 / Published: 14 June 2011
(This article belongs to the Special Issue Distance in Information and Statistical Physics Volume 2)
The Gibbs distribution of statistical physics is an exponential family of probability distributions, which has a mathematical basis of duality in the form of the Legendre transformation. Recent studies of complex systems have found lots of distributions obeying the power law rather than the standard Gibbs type distributions. The Tsallis q-entropy is a typical example capturing such phenomena. We treat the q-Gibbs distribution or the q-exponential family by generalizing the exponential function to the q-family of power functions, which is useful for studying various complex or non-standard physical phenomena. We give a new mathematical structure to the q-exponential family different from those previously given. It has a dually flat geometrical structure derived from the Legendre transformation and the conformal geometry is useful for understanding it. The q-version of the maximum entropy theorem is naturally induced from the q-Pythagorean theorem. We also show that the maximizer of the q-escort distribution is a Bayesian MAP (Maximum A posteriori Probability) estimator. View Full-Text
Keywords: q-exponential family; q-entropy; information geometry; q-Pythagorean theorem; q-Max-Ent theorem; conformal transformation q-exponential family; q-entropy; information geometry; q-Pythagorean theorem; q-Max-Ent theorem; conformal transformation
Show Figures

Graphical abstract

MDPI and ACS Style

Amari, S.-i.; Ohara, A. Geometry of q-Exponential Family of Probability Distributions. Entropy 2011, 13, 1170-1185. https://doi.org/10.3390/e13061170

AMA Style

Amari S-i, Ohara A. Geometry of q-Exponential Family of Probability Distributions. Entropy. 2011; 13(6):1170-1185. https://doi.org/10.3390/e13061170

Chicago/Turabian Style

Amari, Shun-ichi; Ohara, Atsumi. 2011. "Geometry of q-Exponential Family of Probability Distributions" Entropy 13, no. 6: 1170-1185. https://doi.org/10.3390/e13061170

Find Other Styles

Article Access Map by Country/Region

1
Only visits after 24 November 2015 are recorded.
Search more from Scilit
 
Search
Back to TopTop