Newton diagram and stochastic complexity in mixture of binomial distributions

Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

Volumn 3244, Issue , 2004, Pages 350-364

  Yamazaki, Keisuke ^a   Watanabe, Sumio ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; COMPUTATIONAL COMPLEXITY; INTEGRATION; MARKOV PROCESSES; MATHEMATICAL MODELS; MONTE CARLO METHODS; NEURAL NETWORKS; ALGEBRA; BAYESIAN NETWORKS; BINS; COMPLEX NETWORKS; LEARNING SYSTEMS; MIXTURES; STOCHASTIC MODELS;

BAYESIAN ESTIMATION; BINOMIAL DISTRIBUTIONS; HIDDEN MARKOV MODELS; STOCHASTIC COMPLEXITY; BAYESIAN ESTIMATIONS; BINOMIAL DISTRIBUTION; GEOMETRICAL METHODS; INFORMATION ENGINEERINGS; MARKOV CHAIN MONTE-CARLO; MATHEMATICAL FOUNDATIONS; VARIATIONAL-BAYES METHOD;

LEARNING SYSTEMS; STOCHASTIC SYSTEMS;

EID: 15344345474     PISSN: 03029743     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1007/978-3-540-30215-5_27     Document Type: Conference Paper

References (25)

1. Akaike,H. : Likelihood and Bayes procedure. Bayesian Statistics, (Bernald J.M. eds.) University Press, Valencia, Spain, (1980) 143-166
2. Amari, S. and Ozeki, T. : Differential and algebraic geometry of multilayer perceptrons. IEICE Trans, E84-A 1, (2001) 31-38
3. Aranson, A. B. : Computation and applications of the Newton polyhedrons. Mathematics and Computers in Simulation, 57, (2001) 155-160
4. Dacunha-Castelle, D. and Gassiat, E. : Testing in locally conic models, and application to mixture models. Probability and Statistics, 1 (1997) 285-317
5. Ewald, G : Combinatorial convexity and algebraic geometry. Graduate texts in mathematics, 168, Springer-Verlag New York (1996)
6. Fulton, W. : Introduction to toric varieties. Annals of Mathematics Studies, 131, Princeton University Press (1993)
7. Glazko, G. B., Milanesi, L. and Rogozin, I. B. : The subclass approach for mutational spectrum analysis: Application of the SEM algorithm. Journal of Theor. Biology, 192 (1998) 475-487
8. Hagiwara, K. : On the problem in model selection of neural network regression in overrealizable scenario. Neural Computation, 14 (2002) 1979-2002
9. Hartigan, J. A. : A Failure of likelihood asymptotics for normal mixtures. Proceedings of the Berkeley Conference in Honor of J.Neyman and J.Kiefer, 2 (1985) 807-810
10. Levin, E., Tishby, N., and Solla,S.A. : A statistical approaches to learning and generalization in layered neural networks. Proc. of IEEE, 78 (10) (1990) 1568-1674
11. Mackay, D. J. : Bayesian interpolation. Neural Computation, 4 (2) (1992) 415-447
12. Rissanen, J. : Stochastic complexity and modeling. Annals of Statistics, 14 (1986) 1080-1100
13. Schwarz, G. : Estimating the dimension of a model. Annals of Statistics, 6 (2) (1978) 461-464
14. Watanabe, S. : Algebraic analysis for singular statistical estimation. Lecture Notes on Computer Science, 1720 (1999) 39-50, Springer
15. Watanabe, S. : Algebraic analysis for non-identifiable learning machines. Neural Computation, 13 (4) (2001) 899-933
16. Watanabe, S. : Algebraic geometrical methods for hierarchical learning machines. Neural Networks, 14 (8) (2001) 1049-1060
17. Watanabe, S. : Algebraic information geometry for learning machines with singularities. Advances in Neural Information Processing Systems, MIT Press, 14 (2001) 329-336
18. Watanabe, S.: Resolution of singularities and weak convergence of Bayesian stochastic complexity. Proc. of International Workshop on Singular Models and Geometric Methods in Statistics. Institute of Statistical Mathematics (2002) 156-165
19. Watanabe, S. and Fukumizu, K. : Probabilistic design of layered neural networks based on their unified framework. IEEE Trans, on Neural Networks, 6 (3) (1995) 691-702
20. Yamanishi, K. : A decision-theoretic extension of stochastic complexity and its applications to learning. IEEE Trans, on Information Theory, 44 (4) (1998) 1424-1439
21. Yamazaki, K. and Watanabe, S. : A probabilistic algorithm to calculate the learning curves of hierarchical learning machines with singularities, Trans, on IEICE, J85-D-2 3 (2002) 363-372, the English version will appear in Electronics and Communications in Japan.
22. Yamazaki, K. and Watanabe, S. : Singularities in mixture models and upper bounds of stochastic complexity. International Journal of Neural Networks, 16 (2003) 1029-1038
23. Yamazaki, K. and Watanabe, S. : Stochastic complexity of Bayesian networks. Proc. of UAI 2003 (2003) 592-599
24. Yamazaki, K. and Watanabe, S. : Stochastic complexities of hidden Markov models. Proc. of NNSP 2003 (2003) 179-188
25. Yamazaki, K., Aoyagi, M. and Watanabe, S.: Stochastic complexity and Newton diagram. Proc. of International Symposium on Information Theory and its Applications, ISITA2004 to appear