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

DOI10.1080/03610920903140288zbMath1188.62188OpenAlexW2148126650MaRDI QIDQ3562430

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

Rademacher complexitysample complexitymulti-class support vector machinesgeneralized VC dimensions

Mathematics Subject Classification ID

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

Related Items (1)

Combining Multi-class SVMs with Linear Ensemble Methods that Estimate the Class Posterior Probabilities

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Efficient distribution-free learning of probabilistic concepts
• Characterizations of learnability for classes of \(\{0,\dots,n\}\)-valued functions
• On the density of families of sets
• 10.1162/15324430260185628
• Theory of Classification: a Survey of Some Recent Advances
• 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
• Multicategory Support Vector Machines

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