Learning a priori constrained weighted majority votes

DOI10.1007/S10994-014-5462-ZMaRDI QIDQ2512901zbMATH OpenOpenAlexFDO

Authors Aurélien Bellet, Amaury Habrard, Emilie Morvant, Marc Sebban

Publication date 2 February 2015

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-014-5462-z

zbMATH Keywords

nearest neighborsensemble learningPAC-Bayesian boundssample compressionweighted majority vote

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Voting theory (91B12)

Recommendations

• Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm
• The weighted majority algorithm
• A weight-adjusted voting algorithm for ensembles of classifiers
• Combining predictions in pairwise classification: an optimal adaptive voting strategy and its relation to weighted voting
• scientific article; zbMATH DE number 67638

Cites work

• scientific article; zbMATH DE number 5957470 (Why is no real title available?)
• scientific article; zbMATH DE number 893887 (Why is no real title available?)
• Bagging predictors
• Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension
• Computer Vision - ECCV 2004
• Distance metric learning for large margin nearest neighbor classification
• Improved boosting algorithms using confidence-rated predictions
• Learning with decision lists of data-dependent features
• PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification
• Pattern classification.
• Random forests
• Simplified PAC-Bayesian margin bounds.
• Tighter PAC-Bayes bounds through distribution-dependent priors

Cited in

(7)

• Fast greedy \(\mathcal{C} \)-bound minimization with guarantees
• Combining predictions in pairwise classification: an optimal adaptive voting strategy and its relation to weighted voting
• Sparse weighted voting classifier selection and its linear programming relaxations
• Few-shot regression with differentiable reference model
• Majority judgment over a convex candidate space
• Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm
• Real-valued embeddings and sketches for fast distance and similarity estimation

Describes a project that uses

Uses Software

• LMNN

This page was built for publication: Learning a priori constrained weighted majority votes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2512901)