Abstract
We describe the setting of parametric statistics, that is, families of probability measures on a sample space, its task, that is, to identify a particular probability measure that best fits that sampling distribution, and the surprisingly rich and useful geometric structure underlying this. The latter is the topic of this book. A basic geometry quantity, the Fisher metric, a 2-tensor, measures how sensitively the distributions depend on the samples, and this leads to the Cramér–Rao inequality. It is naturally invariant under sufficient statistics, and so is a natural 3-tensor, the Amari–Chentsov tensor. In this introduction, these basic concepts and their functorial properties are described in an informal manner, and an overview of the main ideas and results of the book is given. We also provide a short historical account of the development of the theory.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amari, S.: Theory of information spaces. A geometrical foundation of statistics. POST RAAG Report 106 (1980)
Amari, S.: Differential geometry of curved exponential families curvature and information loss. Ann. Stat. 10, 357–385 (1982)
Amari, S.: Differential-Geometric Methods in Statistics. Lecture Notes in Statistics, vol. 28. Springer, Heidelberg (1985)
Amari, S.: Differential geometrical theory of statistics. In: Differential Geometry in Statistical Inference, Institute of Mathematical Statistics, California. Lecture Notes–Monograph Series, vol. 10 (1987)
Amari, S.: Information Geometry and Its Applications. Applied Mathematical Sciences, vol. 194. Springer, Berlin (2016)
Amari, S., Armstrong, J.: Curvature of Hessian manifolds. Differ. Geom. Appl. 33, 1–12 (2014)
Amari, S., Kurata, K., Nagaoka, H.: Information geometry of Boltzmann machines. IEEE Trans. Neural Netw. 3, 260–271 (1992)
Amari, S., Nagaoka, H.: Methods of Information Geometry. Translations of Mathematical Monographs, vol. 191. Am. Math. Soc./Oxford University Press, Providence/London (2000)
Ay, N., Jost, J., Lê, H.V., Schwachhöfer, L.: Information geometry and sufficient statistics. Probab. Theory Relat. Fields 162, 327–364 (2015)
Ay, N., Tuschmann, W.: Dually flat manifolds and global information geometry. Open Syst. Inf. Dyn. 9, 195–200 (2002)
Balian, R., Alhassid, Y., Reinhardt, H.: Dissipation in many-body systems: a geometric approach based on information theory. Phys. Rep. 131, 1–146 (1986)
Barndorff-Nielsen, O.: Information and Exponential Families in Statistical Theory. Wiley Series in Probability and Mathematical Statistics. John Wiley & Sons, Ltd., Chichester (2014)
Barndorff-Nielsen, O.E., Jupp, P.E.: Approximating exponential models. Ann. Inst. Stat. Math. 41, 247–267 (1989)
Bauer, M., Bruveris, M., Michor, P.: Uniqueness of the Fisher–Rao metric on the space of smooth densities. Bull. Lond. Math. Soc. (2016). arXiv:1411.5577. doi:10.1112/blms/bdw020
Bengtsson, I., Życzkowski, K.: Geometry of Quantum States. Cambridge University Press, Cambridge (2006)
Blackwell, D.: Equivalent comparisons of experiments. Ann. Math. Stat. 24, 265–272 (1953)
Calin, O., Udrişte, C.: Geometric Modeling in Probability and Statistics. Springer, Berlin (2014)
Campbell, L.L.: An extended Chentsov characterization of a Riemannian metric. Proc. Am. Math. Soc. 98, 135–141 (1986)
Cheng, S.Y., Yau, S.T.: The real Monge–Ampère equation and affine flat structures. In: Chern, S.S., Wu, W.T. (eds.) Differential Geometry and Differential Equations. Proc. Beijing Symp., vol. 1980, pp. 339–370 (1982)
Chentsov, N.: Geometry of the “manifold” of a probability distribution. Dokl. Akad. Nauk SSSR 158, 543–546 (1964) (Russian)
Chentsov, N.: Category of mathematical statistics. Dokl. Akad. Nauk SSSR 164, 511–514 (1965)
Chentsov, N.: A systematic theory of exponential families of probability distributions. Teor. Veroâtn. Primen. 11, 483–494 (1966) (Russian)
Chentsov, N.: A nonsymmetric distance between probability distributions, entropy and the theorem of Pythagoras. Mat. Zametki 4, 323–332 (1968) (Russian)
Chentsov, N.: Statistical Decision Rules and Optimal Inference, vol. 53. Nauka, Moscow (1972) (in Russian); English translation in: Math. Monograph., vol. 53. Am. Math. Soc., Providence (1982)
Csiszár, I.: Information-type measures of difference of probability distributeions and indirect observations. Studia Sci. Math. Hung. 2, 299–318 (1967)
Csiszár, I.: On topological properties of \(f\)-divergences. Studia Sci. Math. Hung. 2, 329–339 (1967)
Csiszár, I.: Information measures: a critical survey. In: Proceedings of 7th Conference on Information Theory, Prague, Czech Republic, pp. 83–86 (1974)
Csiszár, I.: I-divergence geometry of probability distributions and minimization problems. Ann. Probab. 3, 146–158 (1975)
Csiszár, I., Matúš, F.: Information projections revisited. IEEE Trans. Inf. Theory 49, 1474–1490 (2003)
Diaconis, P., Sturmfels, B.: Algebraic algorithms for sampling from conditional distributions. Ann. Stat. 26(1), 363–397 (1998)
Drton, M., Sturmfels, B., Sullivant, S.: Lectures on Algebraic Statistics (Oberwolfach Seminars). Birkhäuser, Basel (2009)
Efron, B.: Defining the curvature of a statistical problem (with applications to second order efficiency). Ann. Stat. 3, 1189–1242 (1975), with a discussion by C.R. Rao, Don A. Pierce, D.R. Cox, D.V. Lindley, Lucien LeCam, J.K. Ghosh, J. Pfanzagl, Niels Keiding, A.P. Dawid, Jim Reeds and with a reply by the author
Efron, B.: The geometry of exponential families. Ann. Stat. 6, 362–376 (1978)
Eguchi, S.: Second order efficiency of minimum contrast estimators in a curved exponential family. Ann. Stat. 11, 793–803 (1983)
Eguchi, S.: A characterization of second order efficiency in a curved exponential family. Ann. Inst. Stat. Math. 36, 199–206 (1984)
Eguchi, S.: Geometry of minimum contrast. Hiroshima Math. J. 22, 631–647 (1992)
Geiger, D., Meek, C., Sturmfels, B.: On the toric algebra of graphical models. Ann. Stat. 34(5), 1463–1492 (2006)
Gibilisco, P., Pistone, G.: Connections on non-parametric statistical models by Orlicz space geometry. Infin. Dimens. Anal. Quantum Probab. Relat. Top. 1(2), 325–347 (1998)
Gibilisco, P., Riccomagno, E., Rogantin, M.P., Wynn, H.P. (eds.): Algebraic and Geometric Methods in Statistics. Cambridge University Press, Cambridge (2010)
Hofrichter, J., Jost, J., Tran, T.D.: Information Geometry and Population Genetics. Springer, Berlin (2017)
Jeffreys, H.: An invariant form for the prior probability in estimation problems. Proc. R. Soc. Lond. Ser. A 186, 453–461 (1946)
Jeffreys, H.: Theory of Probability, 2nd edn. Clarendon Press, Oxford (1948)
Jost, J.: Geometry and Physics. Springer, Berlin (2009)
Kass, R., Vos, P.W.: Geometrical Foundations of Asymptotic Inference. Wiley, New York (1997)
Lauritzen, S.: Statistical manifolds. In: Differential Geometry in Statistical Inference, Institute of Mathematical Statistics, California. Lecture Note-Monograph Series, vol. 10 (1987)
Lauritzen, S.: Graphical Models. Oxford University Press, London (1996)
Lê, H.V.: The uniqueness of the Fisher metric as information metric. Ann. Inst. Stat. Math. 69, 879–896 (2017). doi:10.1007/s10463-016-0562-0
Morozova, E., Chentsov, N.: Invariant linear connections on the aggregates of probability distributions. Akad. Nauk SSSR Inst. Prikl. Mat. Preprint, no 167 (1988) (Russian)
Morozova, E., Chentsov, N.: Markov invariant geometry on manifolds of states. Itogi Nauki Tekh. Ser. Sovrem. Mat. Prilozh. Temat. Obz. 6, 69–102 (1990)
Morozova, E., Chentsov, N.: Natural geometry on families of probability laws. Itogi Nauki Tekh. Ser. Sovrem. Mat. Prilozh. Temat. Obz. 83, 133–265 (1991)
Morse, N., Sacksteder, R.: Statistical isomorphism. Ann. Math. Stat. 37, 203–214 (1966)
Murray, M., Rice, J.: Differential Geometry and Statistics. Chapman & Hall, London (1993)
Nagaoka, H., Amari, S.: Differential geometry of smooth families of probability distributions. Dept. of Math. Eng. and Instr. Phys. Univ. of Tokyo. Technical Report METR 82-7 (1982)
Pachter, L., Sturmfels, B. (eds.): Algebraic Statistics for Computational Biology. Cambridge University Press, Cambridge (2005)
Petz, D.: Quantum Information Theory and Quantum Statistics (Theoretical and Mathematical Physics). Springer, Berlin (2007)
Pistone, G., Riccomagno, E., Wynn, H.P.: Algebraic Statistics: Computational Commutative Algebra in Statistics. Chapman & Hall, London (2000)
Pistone, G., Sempi, C.: An infinite-dimensional structure on the space of all the probability measures equivalent to a given one. Ann. Stat. 23(5), 1543–1561 (1995)
Rao, C.R.: Information and the accuracy attainable in the estimation of statistical parameters. Bull. Calcutta Math. Soc. 37, 81–89 (1945)
Rao, C.R.: Differential metrics in probability spaces. In: Differential Geometry in Statistical Inference, Institute of Mathematical Statistics, California. Lecture Notes–Monograph Series, vol. 10 (1987)
Shima, H.: The Geometry of Hessian Structures. World Scientific, Singapore (2007)
Wald, A.: Statistical Decision Function. Wiley, New York (1950)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Ay, N., Jost, J., Lê, H.V., Schwachhöfer, L. (2017). Introduction. In: Information Geometry. Ergebnisse der Mathematik und ihrer Grenzgebiete. 3. Folge / A Series of Modern Surveys in Mathematics, vol 64. Springer, Cham. https://doi.org/10.1007/978-3-319-56478-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-56478-4_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-56477-7
Online ISBN: 978-3-319-56478-4
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)