Model selection for small sample regression

Machine Learning

Volumn 48, Issue 1-3, 2002, Pages 9-23

  Chapelle, Olivier ^a   Vapnik, Vladimir ^b   Bengio, Yoshua ^c  

^a UNIVERSITÉ PIERRE ET MARIE CURIE   (France)

^b AT AND T LABS RESEARCH   (United States)

^c UNIVERSITÉ DE MONTRÉAL   (Canada)

Author keywords

Model selection; Parametric regression; Uniform convergence bounds

Indexed keywords

ASYMPTOTIC STABILITY; BOUNDARY CONDITIONS; CONVERGENCE OF NUMERICAL METHODS; EIGENVALUES AND EIGENFUNCTIONS; ERROR ANALYSIS; FOURIER TRANSFORMS; LEARNING ALGORITHMS; MATHEMATICAL MODELS; MATRIX ALGEBRA; PROBABILITY DISTRIBUTIONS; REGRESSION ANALYSIS; SAMPLING;

COVARIANCE MATRIX; DIRECT EIGENVALUE ESTIMATOR; MODEL SELECTION; PARAMETRIC REGRESSION; PENALIZATION METHOD; SMALL SAMPLE REGRESSION; UNIFORM CONVERGENCE BOUNDS;

LEARNING SYSTEMS;

EID: 0036643075     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1013943418833     Document Type: Article

References (15)

1. Statistical predictor identification
2. Information theory and an extension of the maximum likelihood principle
3. The minimum description length principle in coding and modeling
4. Model selection and error estimation
5. Comparison of VC method with classical methods for model selection
6. The risk inflation criterion for multiple regression
7. p
8. Stochastic complexity and modeling
9. A new metric-based approach to model selection
10. Estimating the dimension of a model
11. An optimal selection of regression variables
12. Generalized cross-validation as a method for choosing a good ridge parameter