Comments on: Support vector machines maximizing geometric margins for multi-class classification

DOI10.1007/s11750-014-0340-1zbMath1336.62180OpenAlexW1978410740MaRDI QIDQ5965492

Yann Guermeur

Publication date: 23 May 2016

Published in: Top (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11750-014-0340-1

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Multi-objective and goal programming (90C29) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multicategory classification by support vector machines
• Efficient distribution-free learning of probabilistic concepts
• Toward efficient agnostic learning
• Entropy and the combinatorial dimension
• Combining discriminant models with new multi-class SVMs
• Characterizations of learnability for classes of \(\{0,\dots,n\}\)-valued functions
• Local Rademacher complexities
• 10.1162/15324430260185628
• 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
• The Generic Chaining
• Multicategory Support Vector Machines
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities

This page was built for publication: Comments on: Support vector machines maximizing geometric margins for multi-class classification