Combining PAC-Bayesian and generic chaining bounds

MaRDI QIDQ3174104zbMATH OpenFDO

Authors Jean-Yves Audibert, Olivier Bousquet

Publication date 12 October 2011

Full work available at URL http://www.jmlr.org/papers/v8/audibert07a.html

zbMATH Keywords

generalization error boundsPAC-Bayes theoremsstatistical learning theory

Mathematics Subject Classification ID

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

Recommendations

• PAC-Bayesian bounds for randomized empirical risk minimizers
• Tighter PAC-Bayes bounds through distribution-dependent priors
• Empirical margin distributions and bounding the generalization error of combined classifiers
• Bounding the generalization error of convex combinations of classifiers: Balancing the dimensionality and the margins.
• PAC-Bayes bounds for supervised classification

Cited in

(7)

• Generic chaining and the \(\ell _{1}\)-penalty
• On PAC-Bayesian bounds for random forests
• \(L_{p}\)-norm Sauer-Shelah lemma for margin multi-category classifiers
• Theory of Classification: a Survey of Some Recent Advances
• User-friendly Introduction to PAC-Bayes Bounds
• Information-theoretic generalization bounds for transductive learning and its applications
• Generalization bounds: perspectives from information theory and PAC-Bayes

This page was built for publication: Combining PAC-Bayesian and generic chaining bounds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3174104)