Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm

MaRDI QIDQ5502136zbMATH OpenFDO

Authors Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand, Jean-Francis Roy

Publication date 17 August 2015

Full work available at URL https://arxiv.org/abs/1503.08329, http://jmlr.csail.mit.edu/papers/v16/germain15a.html

zbMATH Keywords

ensemble methodslearning theorymajority votePAC-Bayesian theorysample compression

Mathematics Subject Classification ID

Bayesian inference (62F15) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Learning a priori constrained weighted majority votes
• scientific article; zbMATH DE number 5957470
• scientific article; zbMATH DE number 2044039
• Boosting a weak learning algorithm by majority
• Learning Theory and Kernel Machines

Cited in

(15)

• Adaptive transfer learning
• Fast greedy \(\mathcal{C} \)-bound minimization with guarantees
• On PAC-Bayesian bounds for random forests
• Learning a priori constrained weighted majority votes
• scientific article; zbMATH DE number 5957470 (Why is no real title available?)
• scientific article; zbMATH DE number 2044039 (Why is no real title available?)
• scientific article; zbMATH DE number 7626742 (Why is no real title available?)
• A reduced-rank approach to predicting multiple binary responses through machine learning
• Machine truth serum: a surprisingly popular approach to improving ensemble methods
• User-friendly Introduction to PAC-Bayes Bounds
• Erratum to: ``Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm
• High-dimensional sparse classification using exponential weighting with empirical hinge loss
• A sparse PAC-Bayesian approach for high-dimensional quantile prediction
• Uniform generalization bounds on data-dependent hypothesis sets via PAC-Bayesian theory on random sets
• Generalization bounds: perspectives from information theory and PAC-Bayes

Describes a project that uses

Uses Software

• UCI
• BayesDA
• MNIST
• Scikit

This page was built for publication: Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5502136)