Random classification noise defeats all convex potential boosters

DOI10.1007/S10994-009-5165-ZMaRDI QIDQ1959553zbMATH OpenOpenAlexWikidataFDO

Authors Philip M. Long, Rocco A. Servedio

Publication date 7 October 2010

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-009-5165-z

zbMATH Keywords

boostinglearning theoryconvex lossnoise-tolerant learningmisclassification noisepotential boosting

Mathematics Subject Classification ID

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

Recommendations

• Boosting in the presence of noise
• 10.1162/153244304773936072
• scientific article; zbMATH DE number 1804119
• A geometric approach to leveraging weak learners
• scientific article; zbMATH DE number 2089370

Cites work

• 10.1162/153244304773936072
• 10.1162/153244304773936108
• A decision-theoretic generalization of on-line learning and an application to boosting
• A geometric approach to leveraging weak learners
• AdaBoost is consistent
• Additive logistic regression: a statistical view of boosting. (With discussion and a rejoinder by the authors)
• An adaptive version of the boost by majority algorithm
• Boosting a weak learning algorithm by majority
• Boosting in the presence of noise
• Boosting with early stopping: convergence and consistency
• Improved boosting algorithms using confidence-rated predictions
• Learning Theory
• On the Bayes-risk consistency of regularized boosting methods.
• Population theory for boosting ensembles.
• Soft margins for AdaBoost
• Statistical behavior and consistency of classification methods based on convex risk minimization.

Cited in

(17)

• Surprising properties of dropout in deep networks
• A non-intrusive correction algorithm for classification problems with corrupted data
• On the noise estimation statistics
• Robust algorithms via PAC-Bayes and Laplace distributions
• Robustness of learning algorithms using hinge loss with outlier indicators
• Learning Theory
• Robust support vector machines for classification with nonconvex and smooth losses
• Binary classification with corrupted labels
• Boosting in the presence of noise
• Soft-max boosting
• The risk of trivial solutions in bipartite top ranking
• Boosting in the presence of outliers: adaptive classification with nonconvex loss functions
• Classification with asymmetric label noise: consistency and maximal denoising
• scientific article; zbMATH DE number 6982911 (Why is no real title available?)
• 10.1162/1532443041424319
• A Framework of Learning Through Empirical Gain Maximization
• scientific article; zbMATH DE number 7370646 (Why is no real title available?)

Describes a project that uses

Uses Software

• AdaBoost.MH

This page was built for publication: Random classification noise defeats all convex potential boosters

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1959553)