Abstract
Information geometry emerged from studies on invariant properties of a manifold of probability distributions. It includes convex analysis and its duality as a special but important part. Here, we begin with a convex function, and construct a dually flat manifold. The manifold possesses a Riemannian metric, two types of geodesics, and a divergence function. The generalized Pythagorean theorem and dual projections theorem are derived therefrom. We construct alpha-geometry, extending this convex analysis. In this review, geometry of a manifold of probability distributions is then given, and a plenty of applications are touched upon. Appendix presents an easily understable introduction to differential geometry and its duality.
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 Statistics, vol. 28. Springer, Heidelberg (1985)
Amari, S.: Differential geometry of a parametric family of invertible linear systems-Riemannian metric, dual affine connections and divergence. Mathematical Systems Theory 20, 53–82 (1987)
Amari, S.: Information geometry of the EM and em algorithms for neural networks. Neural Networks 8-9, 1379–1408 (1995)
Amari, S.: Natural gradient works efficiently in learning. Neural Computation 10, 251–276 (1998)
Amari, S.: Information geometry on hierarchy of probability distributions. IEEE Transactions on Information Theory 47, 1701–1711 (2001)
Amari, S., Kawanabe, M.: Information geometry of estimating functions in semi parametric statistical models. Bernoulli. 3(1), 29–54 (1997)
Amari, S., Kurata, K., Nagaoka, H.: Information geometry of Boltzmann machines. IEEE Transactions on Neural Networks 3, 260–271 (1992)
Amari, S., Nagaoka, H.: Methods of Information Geometry. Translations of Mathematical Monographs, vol. 191. AMS & Oxford University Press (2000)
Amari, S., Park, H., Ozeki, T.: Singularities affect dynamics of learning in neuromanifolds. Neural Computation 18, 1007–1065 (2006)
Bregman, L.M.: The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming. USSR Computational Mathematics and Physics 7, 200–217 (1967)
Byrne, W.: Alternating minimization and Boltzmann machine learning. IEEE Transactions on Neural Networks 3, 612–620 (1992)
Chentsov (ÄŒencov), N.N.: Statistical Decision Rules and Optimal Inference. American Mathematical Society, Rhode Islandm U.S.A. (1982); originally published in Russian, Nauka, Moscow (1972)
Cichocki, A., Amari, S.: Adaptive Blind Signal and Image Processing. John Wiley, Chichester (2002)
Csiszár, I.: I-divergence geometry of probability distributions and minimization problems. The Annals of Probability 3, 146–158 (1975)
Csiszár, I., Tusnády, G.: Information geometry and alternating minimization procedures. In: Dedewicz, E.F., et al. (eds.) Statistics and Decisions, vol. (1), pp. 205–237. R. Oldenbourg Verlag, Munich (1984)
Ikeda, S., Tanaka, T., Amari, S.: Stochastic reasoning, free energy, and information geometry. Neural Computation 16, 1779–1810 (2004)
Lebanon, G.: Riemannian Geometry and Statistical Machine Learning. CMU-LTI-05-189, Carnegie-Mellon University (2005)
Lebanon, G., Lafferty, J.: Boosting and maximum likelihood for exponential models. Advances in Neural Information Processing Systems, vol. 14, pp. 447–451. MIT Press, Cambridge (2002)
Matsushima, Y.: The alpha EM algorithms: Surrogate likelihood maximization using alpha-logarithmic information measures. IEEE Transactions on Information Theory 49, 692–706 (2003)
Murata, N., Takenouchi, T., Kanamori, T., Eguchi, S.: Information geometry of U-boost and Bregman divergence. Neural Computation 16, 1437–1481 (2004)
Nakahara, H., Amari, S.: Information-geometric measure for neural spikes. Neural Computation 14, 2269–2316 (2002)
Nomizu, K., Sasaki, T.: Affine Differential Geometry. Cambridge University Press, Cambridge (1994)
Ohara, A.: Geodesics for dual connections and means on symmetric cone. Interal Equation and Operator Theory 50, 537–548 (2004)
Ohara, A., Tsuchiya, T.: An information geometric approach to polynomial-time interior-pint algorithms (submitted, 2008)
Rényi, A.: On measures of entropy and information. In: Proceedings of the 4th Berkeley Symposium on Mathematical Statistics and Probability, vol. 1, pp. 547–561. University of California Press (1961)
Tsallis, C.: Possible generalization of Boltzmann-Gibbs statistics. Journal of Statistical Physics 52, 479 (1988)
Wu, S., Amari, S.: Conformal transformation of kernel functions: A data-dependent way to improve support vector machine classifiers. Neural Processing Letters 15, 59–67 (2002)
Zhang, J.: Divergence function, duality, and convex analysis. Neural Computation 16, 159–195 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Amari, Si. (2009). Information Geometry and Its Applications: Convex Function and Dually Flat Manifold. In: Nielsen, F. (eds) Emerging Trends in Visual Computing. ETVC 2008. Lecture Notes in Computer Science, vol 5416. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-00826-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-00826-9_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-00825-2
Online ISBN: 978-3-642-00826-9
eBook Packages: Computer ScienceComputer Science (R0)