← Back to papers
2007 JMLR JMLR 2007

AdaBoost is Consistent

Abstract

The risk, or probability of error, of the classifier produced by the AdaBoost algorithm is investigated. In particular, we consider the stopping strategy to be used in AdaBoost to achieve universal consistency. We show that provided AdaBoost is stopped after n1-ε iterations---for sample size n and ε ∈ (0,1)---the sequence of risks of the classifiers it produces approaches the Bayes risk. [abs] [ pdf ][ bib ] © JMLR 2007. (edit, beta)

🧭 Keyword Pioneer — classifier risk
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Data Science & Analytics, Deep Learning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Speech & Audio

Authors

Peter L. Bartlett , Mikhail Traskin

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Statistical Learning

Keywords

risk minimization universal consistency bayes risk classifier risk
Download PDF

Related papers

Statistical Consistency of Kernel Canonical Correlation Analysis 2007
A Probabilistic Analysis of EM for Mixtures of Separated, Spherical Gaussians 2007
Large Margin Semi-supervised Learning 2007
Refinable Kernels 2007
Building Blocks for Variational Bayesian Learning of Latent Variable Models 2007