A moment bound for multi-hinge classifiers

MaRDI QIDQ3096190zbMATH OpenFDO

Authors Bernadetta Tarigan, Sara Van De Geer

Publication date 8 November 2011

Full work available at URL http://www.jmlr.org/papers/v9/tarigan08a.html

zbMATH Keywords

entropymoment boundall-at-oncefast ratemulti-hinge classification

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• On the rate of convergence for multi-category classification based on convex losses
• Multicategory large margin classification methods: hinge losses vs. coherence functions
• The consistency of multicategory support vector machines
• Classification with a reject option using a hinge loss
• Classifiers of support vector machine type with \(\ell_1\) complexity regularization

Cited in

(7)

• A study on L2-loss (squared hinge-loss) multiclass SVM
• Hinge-minimax learner for the ensemble of hyperplanes
• Convergence rates of deep ReLU networks for multiclass classification
• Multicategory large margin classification methods: hinge losses vs. coherence functions
• Statistical learnability of smooth boundaries via pairwise binary classification with deep ReLU networks
• On the rate of convergence for multi-category classification based on convex losses
• Fast convergence rates of deep neural networks for classification

This page was built for publication: A moment bound for multi-hinge classifiers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3096190)