Fast greedy C -bound minimization with guarantees

DOI10.1007/S10994-020-05902-7OpenAlexW3088086419MaRDI QIDQ2217455FDOQ2217455

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

Publication date: 29 December 2020

Published in: Machine Learning (Search for Journal in Brave)

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

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 Keywords

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

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Large scale multiple kernel learning
• A decision-theoretic generalization of on-line learning and an application to boosting
• Greedy function approximation: A gradient boosting machine.
• Random forests
• Bagging predictors
• Title not available (Why is that?)
• Learning the kernel matrix with semidefinite programming
• Boosting. Foundations and algorithms.
• A theory of the learnable
• 10.1162/jmlr.2003.3.4-5.723
• Linear programming boosting via column generation
• PAC-Bayesian Generalisation Error Bounds for Gaussian Process Classification
• PAC-Bayesian stochastic model selection
• Some PAC-Bayesian theorems
• PAC-Bayes bounds with data dependent priors
• Risk bounds for the majority vote: from a PAC-Bayesian analysis to a learning algorithm

Uses Software

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

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)