Learning rate of support vector machine for ranking

DOI10.1016/J.JAT.2014.08.004MaRDI QIDQ468458zbMATH OpenOpenAlexFDO

Authors Heng Chen, Di-Rong Chen

Publication date 7 November 2014

Published in Journal of Approximation Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.jat.2014.08.004

zbMATH Keywords

support vector machine\(U\)-statisticranking ruleexcess risk

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Learning rates for regularized least squares ranking algorithm
• \(\ell^{1}\)-norm support vector machine for ranking with exponentially strongly mixing sequence
• Regularized ranking with convex losses and \(\ell^1\)-penalty
• Learning Theory
• Learning Theory

Cites work

• 10.1162/1532443041424319
• Analysis of support vector machines regression
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• Convexity, Classification, and Risk Bounds
• Fast rates for support vector machines using Gaussian kernels
• Learning Theory
• Learning rates of least-square regularized regression
• Learning theory estimates via integral operators and their approximations
• Limit theorems for \(U\)-processes
• On ranking and generalization bounds
• Ranking and empirical minimization of \(U\)-statistics
• Support Vector Machines
• The convergence rate of a regularized ranking algorithm
• Theory of Reproducing Kernels
• \(U\)-processes indexed by Vapnik-Červonenkis classes of functions with applications to asymptotics and bootstrap of \(U\)-statistics with estimated parameters

Cited in

(9)

• A confidence voting process for ranking problems based on support vector machines
• On kernel methods for covariates that are rankings
• Debiased magnitude-preserving ranking: learning rate and bias characterization
• \(\ell^{1}\)-norm support vector machine for ranking with exponentially strongly mixing sequence
• Learning rates for regularized least squares ranking algorithm
• Statistical performance of optimal scoring in reproducing kernel Hilbert spaces
• Probabilistic generative ranking method based on multi-support vector domain description
• Large-scale linear rankSVM
• Optimality of regularized least squares ranking with imperfect kernels

This page was built for publication: Learning rate of support vector machine for ranking

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q468458)