Abstract
In this paper, we obtain the main term of the average stochastic complexity for certain complete bipartite graph-type spin models in Bayesian estimation. We study the Kullback function of the spin model by using a new method of eigenvalue analysis first and use a recursive blowing up process for obtaining the maximum pole of the zeta function which is defined by using the Kullback function. The papers [1,2] showed that the maximum pole of the zeta function gives the main term of the average stochastic complexity of the hierarchical learning model.
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
Watanabe, S.: Algebraic analysis for nonidentifiable learning machines. Neural Computation 13(4), 899–933 (2001)
Watanabe, S.: Algebraic geometrical methods for hierarchical learning machines. Neural Networks 14(8), 1049–1060 (2001)
Akaike, H.: A new look at the statistical model identification. IEEE Trans. on Automatic Control 19, 716–723 (1974)
Takeuchi, K.: Distribution of an information statistic and the criterion for the optimal model. Mathematical Science 153, 12–18 (1976)
Hannan, E.J., Quinn, B.G.: The determination of the order of an autoregression. Journal of Royal Statistical Society Series B 41, 190–195 (1979)
Murata, N.J., Yoshizawa, S.G., Amari, S.: Network information criterion - determining the number of hidden units for an artificial neural network model. IEEE Trans. on Neural Networks 5(6), 865–872 (1994)
Schwarz, G.: Estimating the dimension of a model. Annals of Statistics 6(2), 461–464 (1978)
Rissanen, J.: Universal coding, information, prediction, and estimation. IEEE Trans. on Information Theory 30(4), 629–636 (1984)
Hironaka, H.: Resolution of Singularities of an algebraic variety over a field of characteristic zero. Annals of Math. 79, 109–326 (1964)
Yamazaki, K., Watanabe, S.: Singularities in Complete Bipartite Graph-Type Boltzmann Machines and Upper Bounds of Stochastic Complexities. IEEE Trans. on Neural Networks 16(2), 312–324 (2005)
Nishiyama, Y., Watanabe, S.: Asymptotic Behavior of Free Energy of General Boltzmann Machines in Mean Field Approximation. Technical report of IEICE NC2006 38, 1–6 (2006)
Aoyagi, M., Watanabe, S.: Resolution of Singularities and the Generalization Error with Bayesian Estimation for Layered Neural Network. IEICE Trans. J88-D-II,10, 2112–2124 (2005) (English version: Systems and Computers in Japan John Wiley & Sons Inc. 2005) (in press)
Aoyagi, M.: The zeta function of learning theory and generalization error of three layered neural perceptron. RIMS Kokyuroku, Recent Topics on Real and Complex Singularities (in press)
Aoyagi, M., Watanabe, S.: Stochastic Complexities of Reduced Rank Regression in Bayesian Estimation. Neural Networks 18, 924–933 (2005)
Watanabe, S., Hagiwara, K., Akaho, S., Motomura, Y., Fukumizu, K., Okada, M., Aoyagi, M.: Theory and Application of Learning System. Morikita, p. 195 (Japanese) (2005)
Nagata, K., Watanabe, S.: A proposal and effectiveness of the optimal approximation for Bayesian posterior distribution. In: Workshop on Information-Based Induction Sciences, pp. 99–104 (2005)
Takamatsu, S., Nakajima, S., Watanabe, S.: Generalization Error of Localized Bayes Estimation in Reduced Rank Regression. In: Workshop on Information-Based Induction Sciences, pp. 81–86 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aoyagi, M., Watanabe, S. (2007). Resolution of Singularities and Stochastic Complexity of Complete Bipartite Graph-Type Spin Model in Bayesian Estimation. In: Torra, V., Narukawa, Y., Yoshida, Y. (eds) Modeling Decisions for Artificial Intelligence. MDAI 2007. Lecture Notes in Computer Science(), vol 4617. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73729-2_42
Download citation
DOI: https://doi.org/10.1007/978-3-540-73729-2_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73728-5
Online ISBN: 978-3-540-73729-2
eBook Packages: Computer ScienceComputer Science (R0)