The consistency of multicategory support vector machines

DOI10.1007/s10444-004-7207-1zbMath1092.68087OpenAlexW2046831132MaRDI QIDQ2491223

Dao-Hong Xiang, Di-Rong Chen

Publication date: 29 May 2006

Published in: Advances in Computational Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10444-004-7207-1

zbMATH Keywords

classificationconsistencyreproducing kernel Hilbert spacemisclassification errorsupport vector machineBayes ruleuniversal consistency

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Related Items (8)

Minimax optimal rates of convergence for multicategory classifications ⋮ The learning rate of \(l_2\)-coefficient regularized classification with strong loss ⋮ Behavior of a functional in learning theory ⋮ Coefficient-based regularization network with variance loss for error ⋮ On the rate of convergence for multi-category classification based on convex losses ⋮ The convergence rate for a \(K\)-functional in learning theory ⋮ Generalization performance of multi-category kernel machines ⋮ Error analysis of multicategory support vector machine classifiers

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multicategory classification by support vector machines
• The covering number in learning theory
• Support vector machines are universally consistent
• Support-vector networks
• Regularization networks and support vector machines
• On the mathematical foundations of learning
• 10.1162/15324430152733133
• Capacity of reproducing kernel spaces in learning theory
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators
• 10.1162/153244302760200704
• Multicategory Support Vector Machines
• Theory of Reproducing Kernels
• On the learnability and design of output codes for multiclass problems

This page was built for publication: The consistency of multicategory support vector machines