Theoretical and experimental evaluation of the subspace information criterion

Machine Learning

Volumn 48, Issue 1-3, 2002, Pages 25-50

  Sugiyama, Masashi ^a   Ogawa, Hidemitsu ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Generalization capability; Model selection; Small samples; Subspace information criterion; Supervised learning

Indexed keywords

APPROXIMATION THEORY; COMPUTER SIMULATION; ERROR ANALYSIS; MATHEMATICAL MODELS; MATRIX ALGEBRA; MAXIMUM LIKELIHOOD ESTIMATION; NORMAL DISTRIBUTION; PROBABILITY DENSITY FUNCTION; REGRESSION ANALYSIS;

AKAIKE INFORMATION CRITERION; BAYESIAN INFORMATION CRITERION; ERROR ESTIMATION; GENERALIZATION MEASURE; MINIMUM DESCRIPTION LENGTH CRITERION; MODEL SELECTION; SMALL SAMPLES; SUBSPACE INFORMATION CRITERION; SUPERVISED LEARNING;

LEARNING SYSTEMS;

EID: 0036643042     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1013995402903     Document Type: Article

References (41)

1. A new look at the statistical model identification
2. Likelihood and the Bayes procedure
3. Asymptotic statistical theory of overtraining and cross-validation
4. Theory of reproducing kernels
5. Model complexity control for regression using VC generalization bounds
6. Smoothing noisy data with spline functions: Estimating the correct degree of smoothing by the method of generalized cross-validation
7. Bootstrapping log likelihood and EIC, an extension of AIC
8. Generalized information criterion in model selection
9. On information and sufficiency
10. L and generalized cross-validation in ridge regression with application to spline smoothing
11. Bayesian interpolation
12. Choosing a subset regression
13. P
14. Choosing an algorithm of estimation based on samples of limited size
15. Network information criterion-Determining the number of hidden units for an artificial neural network model
16. Introduction to radial basis function networks
17. Modeling by shortest data description
18. Stochastic complexity
19. Fisher information and stochastic complexity
20. Estimating the dimension of a model
21. An asymptotic equivalence of choice of model by cross-validation and Akaike's Criterion
22. Further analysis of the data by Akaike's information criterion and the finite corrections
23. Functional analytic approach to model selection-Subspace information criterion
24. P and network information criterion as approximation of subspace information criterion
25. Optimal design of regularization term and regularization parameter by subspace information criterion
26. Subspace information criterion for model selection
27. Distribution of information statistics and validity criteria of models
28. On the selection of statistical models by AIC
29. Subspace information criterion for non-quadratic regularizers
30. A decision-theoretic extension of stochastic complexity and its approximation to learning