Sample Complexity of Classifiers Taking Values in ℝQ, Application to Multi-Class SVMs

DOI10.1080/03610920903140288MaRDI QIDQ3562430zbMATH OpenOpenAlexFDO

Authors Yann Guermeur

Publication date 21 May 2010

Published in Communications in Statistics: Theory and Methods (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/03610920903140288

zbMATH Keywords

generalized VC dimensionsmulti-class support vector machinesRademacher complexitysample complexity

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Sample complexity for computational classification problems
• Classifiers of support vector machine type with \(\ell_1\) complexity regularization
• OnL₁-Norm Multiclass Support Vector Machines
• scientific article; zbMATH DE number 5295842
• scientific article; zbMATH DE number 1424219
• A quadratic loss multi-class SVM for which a radius-margin bound applies
• Rademacher complexity bounds for a penalized multi-class semi-supervised algorithm
• The sample complexity of learning linear predictors with the squared loss
• Classification with support vector machines and Kolmogorov-Smirnov bounds

Cites work

• 10.1162/15324430260185628
• Characterizations of learnability for classes of \(\{0,\dots,n\}\)-valued functions
• Efficient distribution-free learning of probabilistic concepts
• scientific article; zbMATH DE number 67611 (Why is no real title available?)
• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 5055767 (Why is no real title available?)
• Multicategory Support Vector Machines
• On the density of families of sets
• Scale-sensitive dimensions, uniform convergence, and learnability
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Theory of Classification: a Survey of Some Recent Advances

Cited in

(7)

• Neurodynamical classifiers with low model complexity
• \(L_{p}\)-norm Sauer-Shelah lemma for margin multi-category classifiers
• VC dimension, fat-shattering dimension, Rademacher averages, and their applications
• Combining multi-class SVMs with linear ensemble methods that estimate the class posterior probabilities
• VC theory of large margin multi-category classifiers
• A quadratic loss multi-class SVM for which a radius-margin bound applies
• Multi-category classifiers and sample width

This page was built for publication: Sample Complexity of Classifiers Taking Values in ℝ^Q, Application to Multi-Class SVMs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3562430)