Fast greedy C -bound minimization with guarantees

DOI10.1007/S10994-020-05902-7MaRDI QIDQ2217455zbMATH OpenOpenAlexFDO

Authors Baptiste Bauvin, Cécile Capponi, Jean-Francis Roy, François Laviolette

Publication date 29 December 2020

Published in Machine Learning (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/s10994-020-05902-7

zbMATH Keywords

boostingensemble methodsgreedy optimizationPAC-Bayes\( \mathcal{C} \)-bound

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm
• Learning a priori constrained weighted majority votes
• On PAC-Bayesian bounds for random forests
• scientific article; zbMATH DE number 2089371
• scientific article; zbMATH DE number 5957470

Cites work

• scientific article; zbMATH DE number 5544465 (Why is no real title available?)
• 10.1162/jmlr.2003.3.4-5.723
• A decision-theoretic generalization of on-line learning and an application to boosting
• A theory of the learnable
• Bagging predictors
• Boosting. Foundations and algorithms.
• Greedy function approximation: A gradient boosting machine.
• Large scale multiple kernel learning
• Learning the kernel matrix with semidefinite programming
• Linear programming boosting via column generation
• PAC-Bayes bounds with data dependent priors
• PAC-Bayesian Generalisation Error Bounds for Gaussian Process Classification
• PAC-Bayesian stochastic model selection
• Random forests
• Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm
• Some PAC-Bayesian theorems

Describes a project that uses

Uses Software

• AdaBoost-SAMME
• MNIST
• AdaBoost.MH
• UCI
• SHOGUN

This page was built for publication: Fast greedy \(\mathcal{C} \)-bound minimization with guarantees

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2217455)