Bounds on the generalization ability of Bayesian inference and Gibbs algorithms

DOI10.1007/3-540-44668-0_38MaRDI QIDQ4787371zbMATH OpenFDO

Authors Hélène Paugam-Moisy, Olivier Teytaud

Publication date 6 January 2003

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/3-540-44668-0_38

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies and applications (68U99) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension
• scientific article; zbMATH DE number 7272386
• Some PAC-Bayesian theorems
• scientific article; zbMATH DE number 5544465

Cited in

(10)

• Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension
• Sufficientness postulates for Gibbs-type priors and hierarchical generalizations
• Suboptimal behavior of Bayes and MDL in classification under misspecification
• General inequalities for Gibbs posterior with nonadditive empirical risk
• PAC-Bayesian Generalisation Error Bounds for Gaussian Process Classification
• scientific article; zbMATH DE number 7219345 (Why is no real title available?)
• Learning Theory
• 10.1162/1532443041424300
• Analysis of Bayesian inference algorithms by the dynamical functional approach
• On generalized computable universal priors and their convergence

This page was built for publication: Bounds on the generalization ability of Bayesian inference and Gibbs algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4787371)