Support vector machines with a reject option

DOI10.3150/10-BEJ320MaRDI QIDQ654412zbMATH OpenFDO

Authors Ming Yuan, Marten H. Wegkamp

Publication date 28 December 2011

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1201.1140

zbMATH Keywords

statistical learningsupport vector machinesclassification with a reject option

Mathematics Subject Classification ID

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

Abstract: This paper studies $el{l}_1$ regularization with high-dimensional features for support vector machines with a built-in reject option (meaning that the decision of classifying an observation can be withheld at a cost lower than that of misclassification). The procedure can be conveniently implemented as a linear program and computed using standard software. We prove that the minimizer of the penalized population risk favors sparse solutions and show that the behavior of the empirical risk minimizer mimics that of the population risk minimizer. We also introduce a notion of classification complexity and prove that our minimizers adapt to the unknown complexity. Using a novel oracle inequality for the excess risk, we identify situations where fast rates of convergence occur.

Recommendations

• scientific article; zbMATH DE number 2089926
• Classification with a reject option using a hinge loss
• Classification methods with reject option based on convex risk minimization
• Lasso type classifiers with a reject option
• Statistical performance of support vector machines

Cites work

• scientific article; zbMATH DE number 49190 (Why is no real title available?)
• scientific article; zbMATH DE number 1420699 (Why is no real title available?)
• Classification methods with reject option based on convex risk minimization
• Classification with a reject option using a hinge loss
• Classification with reject option
• Classifiers of support vector machine type with \(\ell_1\) complexity regularization
• Combinatorial methods in density estimation
• Lasso type classifiers with a reject option
• Optimal aggregation of classifiers in statistical learning.
• Simultaneous analysis of Lasso and Dantzig selector
• Sparsity in penalized empirical risk minimization
• The elements of statistical learning. Data mining, inference, and prediction

Cited in

(21)

• Support vector machine in ultrahigh-dimensional feature space
• Twin SVM with a reject option through ROC curve
• Discussion of ``Correlated variables in regression: clustering and sparse estimation
• Model averaging for support vector classifier by cross-validation
• Incorporating Detractors into SVM Classification
• Error rate control for classification rules in multiclass mixture models
• Classification with a reject option using a hinge loss
• Classifiers of support vector machine type with \(\ell_1\) complexity regularization
• scientific article; zbMATH DE number 2013261 (Why is no real title available?)
• Learning with Rejection
• Large‐margin classification with multiple decision rules
• Lasso type classifiers with a reject option
• Confidence sets with expected sizes for multiclass classification
• On reject and refine options in multicategory classification
• An error bound for \(L_1\)-norm support vector machine coefficients in ultra-high dimension
• Performance measures for classification systems with rejection
• Classification methods with reject option based on convex risk minimization
• scientific article; zbMATH DE number 2089926 (Why is no real title available?)
• Optimal discriminant analysis in high-dimensional latent factor models
• Consistency of plug-in confidence sets for classification in semi-supervised learning
• Outcome weighted learning with a reject option

This page was built for publication: Support vector machines with a reject option

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q654412)