Random classification noise defeats all convex potential boosters

DOI10.1007/s10994-009-5165-zzbMath1470.68139OpenAlexW2490901831WikidataQ56114422 ScholiaQ56114422MaRDI QIDQ1959553

Rocco A. Servedio, Philip M. Long

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

learning theoryboostingconvex 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)

Related Items (14)

Binary classification with corrupted labels ⋮ Classification with asymmetric label noise: consistency and maximal denoising ⋮ A non-intrusive correction algorithm for classification problems with corrupted data ⋮ Unnamed Item ⋮ Robust Support Vector Machines for Classification with Nonconvex and Smooth Losses ⋮ The risk of trivial solutions in bipartite top ranking ⋮ On the noise estimation statistics ⋮ Surprising properties of dropout in deep networks ⋮ Unnamed Item ⋮ Robustness of learning algorithms using hinge loss with outlier indicators ⋮ Robust Algorithms via PAC-Bayes and Laplace Distributions ⋮ Boosting in the Presence of Outliers: Adaptive Classification With Nonconvex Loss Functions ⋮ Soft-max boosting ⋮ A Framework of Learning Through Empirical Gain Maximization

Uses Software

• AdaBoost.MH

Cites Work

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

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