On surrogate loss functions and \(f\)-divergences

DOI10.1214/08-AOS595zbMath1162.62060arXivmath/0510521OpenAlexW3099188570MaRDI QIDQ1020983

Martin J. Wainwright, Michael I. Jordan, XuanLong Nguyen

Publication date: 4 June 2009

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/math/0510521

zbMATH Keywords

discriminant analysis\(f\)-divergencesbinary classificationquantizer designBayes consistencystatistical machine learningAli-Silvey divergencesnonparametric decentralized detectionsurrogate losses

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Computational learning theory (68Q32) Bayesian inference (62F15) Statistical aspects of information-theoretic topics (62B10) Nonparametric inference (62G99)

Related Items

Primal explicit max margin feature selection for nonlinear support vector machines, Unnamed Item, The potential and perils of preprocessing: building new foundations, On distributionally robust extreme value analysis, Optimal shrinkage estimation of predictive densities under \(\alpha\)-divergences, Boosting \(k\)-NN for categorization of natural scenes, An Introduction to Neural Data Compression, On the empirical estimation of integral probability metrics, Minimax optimal sequential hypothesis tests for Markov processes, New perspectives on multilocus ancestry informativeness, Bounding the difference between RankRC and RankSVM and application to multi-level rare class kernel ranking, Multiclass classification, information, divergence and surrogate risk, Sketching information divergences, Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Convex functions, monotone operators and differentiability.
• Process consistency for AdaBoost.
• On the Bayes-risk consistency of regularized boosting methods.
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Support-vector networks
• On the Design and Comparison of Certain Dichotomous Experiments
• Consistency of Support Vector Machines and Other Regularized Kernel Classifiers
• Applications of Ali-Silvey Distance Measures in the Design Generalized Quantizers for Binary Decision Systems
• Some inequalities for information divergence and related measures of discrimination
• 10.1162/153244304773936108
• Nonparametric decentralized detection using kernel methods
• Convex Analysis
• Convexity, Classification, and Risk Bounds
• Equivalent Comparisons of Experiments