Subspace information criterion for nonquadratic regularizers-model selection for sparse regressors

IEEE Transactions on Neural Networks

Volumn 13, Issue 1, 2002, Pages 70-80

  Tsuda, Koji ^a,b   Sugiyama, Masashi ^c   Müller, Klaus Robert ^a,d  

^a FRAUNHOFER FIRST   (Germany)

^b NATIONAL INSTITUTE OF ADVANCED INDUSTRIAL SCIENCE AND TECHNOLOGY AIST   (Japan)

^c TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

^d UNIVERSITY OF POTSDAM   (Germany)

Author keywords

Kernel methods; Model selection; Regularization; Sparse regressors; Subspace information criterion (SIC)

Indexed keywords

ASYMPTOTIC STABILITY; LEARNING ALGORITHMS; MATHEMATICAL MODELS; NORMAL DISTRIBUTION; OPTIMIZATION; REGRESSION ANALYSIS;

GENERALIZED SUBSPACE INFORMATION CRITERION; KERNEL METHODS; MODEL SELECTION; NETWORK INFORMATION CRITERION; NONQUADRATIC REGULARIZERS; NORM REGULARIZERS; SPARSE REGRESSORS;

INFORMATION USE;

EID: 0036130853     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.977272     Document Type: Article

References (37)

1. Regularization algorithms for learning that are equivalent to multilayer networks
2. Introduction to radial basis function networks
3. Model complexity control for regression using VC generalization bounds
4. Network information criterion - Determining the number of hidden units for an artificial neural network model
5. Bias of estimators and regularization terms
6. Subspace information criterion for model selection
7. Inference in an authorship problem. A comparative study of discrimination methods applied to the authorship of the disputed Federalist papers
8. p
9. Likelihood and the bayes procedure
10. Bayesian interpolation
11. A new look at the statistical model identification
12. An adaptive regularization criterion for supervised learning
13. Optimal design of regularization term and regularization parameter by subspace information criterion
14. Bayesian regularization and pruning using a Laplace prior
15. Robust linear programming discrimination of two linearly inseparable sets
16. Mathematical programming in data mining
17. Feature selection via mathematical programming
18. Classification on proximity data with LP-machines
19. Sparse kernel feature analysis
20. Sparse greedy matrix approximation for machine learning
21. Statistical pattern recognition: A review
22. Neural networks and the bias/variance dilemma
23. Bias/variance decompositions for likelihood-based estimators
24. Theoretical and experimental evaluation of subspace information criterion
25. A mathematical programming approach to the kernel fisher algorithm
26. Spline model for observational data
27. Support vector regression with anova decomposition kernels
28. Support vector method for function approximation, regression estimation, and signal processing
29. An application of multiple comparison techniques to model selection