Generalization performance of bipartite ranking algorithms with convex losses

DOI10.1016/J.JMAA.2013.03.033zbMATH Open1304.62044OpenAlexW2083125986MaRDI QIDQ488690FDOQ488690

Fangchao He, Hong Chen

Publication date: 26 January 2015

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jmaa.2013.03.033

Recommendations

• Learning Theory
• Approximation analysis of gradient descent algorithm for bipartite ranking
• Generalization bounds for ranking algorithms via algorithmic stability
• On ranking and generalization bounds
• The convergence rate of a regularized ranking algorithm

zbMATH Keywords

reproducing kernel Hilbert spacegeneralization boundRademacher complexitybipartite ranking

Mathematics Subject Classification ID

Statistical ranking and selection procedures (62F07)

Cites Work

• Theory of Reproducing Kernels
• Learning Theory
• 10.1162/153244302760200704
• On the mathematical foundations of learning
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Title not available (Why is that?)
• Title not available (Why is that?)
• Ranking and empirical minimization of \(U\)-statistics
• 10.1162/153244303321897690
• Title not available (Why is that?)
• Generalization bounds for ranking algorithms via algorithmic stability
• Margin-based ranking and an equivalence between AdaBoost and RankBoost
• Title not available (Why is that?)
• 10.1162/1532443041827916
• Title not available (Why is that?)
• Statistical Analysis of Bayes Optimal Subset Ranking
• Adaptive partitioning schemes for bipartite ranking
• On the ERA ranking representability of pairwise bipartite ranking functions
• A transitivity analysis of bipartite rankings in pairwise multi-class classification
• The convergence rate of a regularized ranking algorithm
• Gradient iteration with \(\ell _{p}\)-norm constraints
• Learning to rank on graphs
• Learning gradients by a gradient descent algorithm
• The \(p\)-norm push: a simple convex ranking algorithm that concentrates at the top of the list
• Generalization performance of least-square regularized regression algorithm with Markov chain samples

Cited In (6)

• Calibration and regret bounds for order-preserving surrogate losses in learning to rank
• Analysis of regularized least squares ranking with centered reproducing kernel
• Learning Theory
• Bias corrected regularization kernel method in ranking
• Learning Theory
• Optimality of regularized least squares ranking with imperfect kernels

This page was built for publication: Generalization performance of bipartite ranking algorithms with convex losses

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q488690)