Covering numbers for support vector machines

IEEE Transactions on Information Theory

Volumn 48, Issue 1, 2002, Pages 239-250

  Guo, Ying ^a,b   Bartlett, Peter L ^a,c   Shawe Taylor, John ^a,d   Williamson, Robert C ^a,b  

^a IEEE   (Australia)

^b AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

^c BIOwulf Technologies   (United States)

^d UNIVERSITY OF LONDON   (United Kingdom)

Author keywords

Covering numbers; Entropy numbers; Kernel machines; Statistical learning theory; Support vector (SV) machines

Indexed keywords

COVERING NUMBERS; ENTROPY NUMBERS; GAUSSIAN KERNEL; INTEGRAL OPERATOR; KERNEL FUNCTION; KERNEL MACHINES; LINEAR CLASSIFIERS; STATISTICAL LEARNING THEORY; SUPPORT VECTOR MACHINES;

EIGENVALUES AND EIGENFUNCTIONS; INTEGRAL EQUATIONS; MATHEMATICAL MODELS; MATHEMATICAL OPERATORS; RADIAL BASIS FUNCTION NETWORKS; STATISTICAL METHODS;

LEARNING ALGORITHMS;

EID: 0036158359     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/18.971752     Document Type: Article

References (16)

1. Probabilistic analysis of learning in artificial neural networks: The pac model and its variants
2. The sample complexity of pattern classification with neural networks: The size of the weights is more important than the size of the network
3. A training algorithm for optimal margin classifiers
4. Support vector networks
5. An equivalence between sparse approximation and support vector machines
6. Structural risk minimization over data-dependent hierarchies
7. Margin distribution bounds on generalization
8. Generalization performance of classifiers in terms of observed covering numbers
9. The connection between regularization operators and support vector kernels
10. Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators
11. Entropy numbers, operators and support vector kernels