Fujiwara, Akio; Amari, Shun-ichi Gradient systems in view of information geometry. (English) Zbl 0883.53020 Physica D 80, No. 3, 317-327 (1995). Summary: Dualistic properties of a gradient flow on a manifold \(M\) associated with a dualistic structure \((g,\nabla, \nabla^*)\) is studied from an information geometrical viewpoint. Some useful applications are also investigated. Cited in 13 Documents MSC: 53B05 Linear and affine connections 37J35 Completely integrable finite-dimensional Hamiltonian systems, integration methods, integrability tests 37K10 Completely integrable infinite-dimensional Hamiltonian and Lagrangian systems, integration methods, integrability tests, integrable hierarchies (KdV, KP, Toda, etc.) 62A01 Foundations and philosophical topics in statistics 94A15 Information theory (general) Keywords:information geometry; gradient flow; dualistic structure; dynamical systems PDF BibTeX XML Cite \textit{A. Fujiwara} and \textit{S.-i. Amari}, Physica D 80, No. 3, 317--327 (1995; Zbl 0883.53020) Full Text: DOI OpenURL References: [1] Karmarkar, N., A new polynomial-time algorithm for linear programming, Combinatorica, 4, 373 (1984) · Zbl 0557.90065 [2] Brockett, R. W., Dynamical systems that sort lists, diagonalize matrices and solve linear prigramming problems, (Proc. 27th IEEE Conf. on Decision and Control (1988), IEEE), 799 · Zbl 0719.90045 [3] Nakamura, Y., A new nonlinear dynamical system that leads to eigenvalues, Jap. J. Industrial and Appl. Math., 9, 133 (1992) · Zbl 0757.58020 [4] Brockett, R. W., Least squares matching problems, Linear Algebra and its appl., 122-124, 761 (1989) · Zbl 0676.90055 [5] Bayer, D. A.; Lagarias, J. C., the nonlinear geometry of linear programming, I and II, Trans. American Math. Soc., 314, 527 (1989) · Zbl 0671.90046 [6] Brockett, R. W., Differential geometry and the design of gradient algorithms, (Greens, R. E.; Yau, S. T., Differential Geometry (1993), Amer. Math. Soc) · Zbl 0559.93042 [7] Abraham, R.; Marsden, J. E., Foundations of Mechanics (1985), Benjamin: Benjamin New York [8] Balian, R.; Alhassid, Y.; Reinhardt, H., Dissipation in many-body systems: A geometric approach based on information theory, Physics Reports, 131, 1 (1986) [9] Amari, S., Differential geometry of curved exponential families - Curvatures and information loss, Ann. Statist., 10, 357 (1982) · Zbl 0507.62026 [10] Amari, S., Differential-Geometrical Methods in Statistics, (Lec. Notes in Statist., 28 (1985), Springer: Springer Berlin) · Zbl 0559.62001 [11] Nagaoka, H.; Amari, S., Differential geometry of smooth families of probability distributions, (METR 82-7 (1982), Univ. Tokyo) [12] Amari, S.; Barndorff-Nielsen, O. E.; Kass, R. E.; Lauritzen, S. L.; Rao, C. R., Differential Geometry in Statistical Inferences, (IMS Lecture Notes Monograph Series, 10 (1987), IMS CA: IMS CA Hayward) · Zbl 0694.62001 [13] Chentsov, N. N., Optimal Decision Rules and Optimal Inference (1982), AMS: AMS Rhode Island, [in English] · Zbl 0484.62008 [14] Kumon, M.; Amari, S., Geometrical theory of higher-order asymptotics of test, interval estimator and conditional inference, (Proc. R. Soc. London A, 387 (1983)), 429 · Zbl 0527.62031 [15] Amari, S.; Kumon, M., Estimation in the presence of infinitely many nuisance parameters - Geometry of estimating functions, Ann. Statist., 16, 1044 (1988) · Zbl 0665.62029 [16] Okamoto, I.; Amari, S.; Takeuchi, K., Asymptotic theory of sequential estimation: Differential geometrical approach, Ann. Stst., 19, 961 (1991) · Zbl 0737.62067 [17] Amari, S., Differential geometry of a parametric family of invertible linear systems - Riemannian metric, dual affine connections and divergence, Math. Systems Theory, 20, 53 (1987) · Zbl 0632.93017 [18] Ohara, A.; Amari, S., Differential geometric structures of stable state feedback systems with dual connections, Kybernetika, 30, 369 (1984) · Zbl 0821.93029 [19] Amari, S.; Han, T. S., Statistical inference under multiterminal rate restrictions - A differential geometrical approach, IEEE Trans. Information Theory IT-35, 217 (1989) · Zbl 0673.62008 [20] Amari, S., Fisher information under restriction of Shannon information in multiterminal situations, Ann. Inst. Statist. Math., 41, 623 (1989) · Zbl 0703.62005 [21] Amari, S.; Kurata, K.; Nagaoka, H., Information geometry of Boltzmann machines, IEEE Trans. Neural Networks, 3, 260 (1992) [22] Obata, T.; Hara, H.; Endo, K., Differential geometry of nonequilibrium processes, Phys. Rev. A, 45, 6997 (1992) [23] Nakamura, Y., Completely integrable gradient systems on the manifolds of Gaussian and multinomial distributions, Jap. J. Industrial and Appl. Math., 10, 179 (1993) · Zbl 0814.58021 [24] Murray, M. K.; Rice, J. W., Differential Geometry and Statistics (1993), Chapman & Hall: Chapman & Hall London · Zbl 0628.22003 [26] Kurose, T., Dual connections and affine geometry, Math. Z., 203, 115 (1990) · Zbl 0696.53005 [27] Hirsch, M. H.; Smale, S., Differential Equations, Dynamical Systems, and Linear Algebra, (Pure and Appl. Math., Vol. 5 (1974), Academic: Academic New York) [28] Lagarias, J. C., The nonlinear geometry of linear programming. III Projective Legendre transform coordinates and Hilbert geometry, Trans. American Math. Soc., 320, 193 (1990) · Zbl 0699.90070 [29] Ackley, D. H.; Hinton, G. E.; Sejnowski, T. J., A learning algorithm for Boltzmann machines, Cognitive Science, 9, 147 (1985) [30] Dempster, A. P.; Laird, N. M.; Rubin, D. B., Maximum likelihood from incomplete data via EM algorithm, J. Royal Stat. Soc. B, 39, 1 (1977) · Zbl 0364.62022 [31] Barns, E. R., A variation on Karmarkar’s algorithm for solving linear programing problems, Math. Programming, 36, 174 (1986) [32] Hofbauer, J.; Sigmund, K., The theory of Evolution and Dynamical Systems (1988), Cambridge Univ. Press: Cambridge Univ. Press Cambridge [33] Akin, E., The Geometry of Population Genetics, (Lec. Notes in Biomath., 31 (1979), Springer: Springer Berlin) · Zbl 0437.92016 This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.