Abstract
In this paper we investigate the dually flat structure of the space of positive definite matrices induced by the class of convex functions called V-potentials from the viewpoints of information geometry. It is proved that the geometry is invariant under special linear group actions. As an application to statistics, we finally give the correspondence between the obtained geometry on positive definite matrices and the one on elliptical distributions induced from a certain Bregman divergence.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Amari, S.: Differential-geometrical methods in statistics. Lecture notes in statist., vol. 28. Springer, New York (1985)
Amari, S., Nagaoka, H.: Methods of information geometry. AMS&OUP (2000)
David, A.P.: The geometry of proper scoring rules. Ann. Inst. Stat. 59, 77–93 (2007)
Eguchi, S.: Information geometry and statistical pattern recognition. Sugaku Expositions, Amer. Math. Soc. 19, 197–216 (2006); Originally Sūgaku, 56, 380–399 (2004) (in Japanese)
Eguchi, S.: Information divergence geometry and the application to statistical machine learning. In: Emmert-Streib, F., Dehmer, M. (eds.) Information Theory and Statistical Learning, pp. 309–332. Springer (2008)
Eguchi, S., Copas, J.: A class of logistic-type discriminant functions. Biometrika 89(1), 1–22 (2002)
Eguchi, S., Komori, O., Kato, S.: Projective power entropy and maximum Tsallis entropy distributions. Entropy 13, 1746–1764 (2011)
Fang, K.T., Kotz, S., Ng, K.W.: Symmetric multivariate and related distributions. Chapman and Hall, London (1990)
Faraut, J., Korányi, A.: Analysis on symmetric cones. Oxford Univ. Press, New York (1994)
Grunwald, P.D., David, A.P.: Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory. Ann. Stat. 32, 1367–1433 (2004)
Helgason, S.: Differential geometry and symmetric spaces. Academic Press, New York (1962)
Kanamori, T., Ohara, A.: A Bregman Extension of quasi-Newton updates I: An Information Geometrical framework. Optimization Methods and Software 28(1), 96–123 (2013)
Koecher, M.: The Minnesota notes on Jordan algebras and their applications. Springer, Berlin (1999)
Muirhead, R.J.: Aspects of multivariate statistical theory. Wiley, New York (1982)
Murata, N., Takenouchi, T., Kanamori, T., Eguchi, S.: Information geometry of U-boost and Bregman divergence. Neural Computation 16, 1437–1481 (2004)
Naudts, J.: Continuity of a class of entropies and relative entropies. Rev. Math. Phys. 16, 809–822 (2004)
Naudts, J.: Estimators, escort probabilities, and φ-exponential families in statistical physics. J. Ineq. Pure Appl. Math. 5, 102 (2004)
Ohara, A.: Geodesics for dual connections and means on symmetric cones. Integral Equations and Operator Theory 50, 537–548 (2004)
Ohara, A., Suda, N., Amari, S.: Dualistic differential geometry of positive definite matrices and its applications to related problems. Linear Algebra Appl. 247, 31–53 (1996)
Ollila, E., Tyler, D., Koivunen, V., Poor, V.: Complex Elliptically Symmetric Distributions: Survey, New Results and Applications. IEEE Trans. Signal Process. 60(11), 5597–5623 (2012)
Rothaus, O.S.: Domains of positivity. Abh. Math. Sem. Univ. Hamburg 24, 189–235 (1960)
Scott, D.W.: Parametric statistical modeling by minimum integrated square error. Technometrics 43, 274–285 (2001)
Shima, H.: The geometry of Hessian structures. World Scientific, Singapore (2007)
Tsallis, C.: Introduction to Nonextensive Statistical Mechanics. Springer, New York (2009)
Vinberg, E.B.: The theory of convex homogeneous cones. Trans. Moscow Math. Soc. 12, 340–430 (1963)
Wolkowicz, H., et al. (eds.): Handbook of semidefinite programming. Kluwer Acad. Publ., Boston (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ohara, A., Eguchi, S. (2013). Geometry on Positive Definite Matrices Induced from V-Potential Function. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2013. Lecture Notes in Computer Science, vol 8085. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40020-9_69
Download citation
DOI: https://doi.org/10.1007/978-3-642-40020-9_69
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40019-3
Online ISBN: 978-3-642-40020-9
eBook Packages: Computer ScienceComputer Science (R0)