Concept learning using complexity regularization

DOI10.1109/18.481777MaRDI QIDQ4879989zbMATH OpenOpenAlexFDO

Authors Kenneth Zeger, Gábor Lugosi

Publication date 1 September 1996

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/18.481777

zbMATH Keywords

approximation errorBayes error probabilityBayes ruleclassificationcomplexity regularizationestimation errorinfinite Vapnis Chervonenkis dimensionlearning theorypattern recognition

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Complexity control in statistical learning
• Local Rademacher complexities
• 10.1162/153244302760200704
• Error analysis on regularized learning
• Statistical learning theory: models, concepts, and results

Cited in

(14)

• Estimation of the conditional risk in classification: the swapping method
• Efficient distribution-free population learning of simple concepts
• On learning multicategory classification with sample queries.
• Model selection in utility-maximizing binary prediction
• A penalized criterion for variable selection in classification
• Complexity control in statistical learning
• Model selection by bootstrap penalization for classification
• Parametric version space approach to concept learning
• Theory of Classification: a Survey of Some Recent Advances
• Adaptive partitioning schemes for bipartite ranking
• scientific article; zbMATH DE number 1400207 (Why is no real title available?)
• Semantic-based regularization for learning and inference
• Sampling and empirical risk minimization
• Multiclass classification with potential function rules: margin distribution and generalization

This page was built for publication: Concept learning using complexity regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4879989)