Generalization bounds for averaged classifiers

DOI10.1214/009053604000000058zbMath1045.62056arXivmath/0410092OpenAlexW3103537123MaRDI QIDQ1879971

Robert E. Schapire, Yishay Mansour, Yoav Freund

Publication date: 15 September 2004

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/math/0410092

zbMATH Keywords

classificationaveragingensemble methodsBayesian methodsgeneralization bounds

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Empirical decision procedures; empirical Bayes procedures (62C12)

Related Items (12)

Concentration inequalities for non-causal random fields ⋮ Limit theorems and inequalities via martingale methods ⋮ Posterior concentration and fast convergence rates for generalized Bayesian learning ⋮ Knows what it knows: a framework for self-aware learning ⋮ Classification with guaranteed probability of error ⋮ Automated trading with boosting and expert weighting ⋮ Theory and algorithms for learning with rejection in binary classification ⋮ Stochastic boosting algorithms ⋮ Theory of Classification: a Survey of Some Recent Advances ⋮ Learning with Rejection ⋮ Deviation inequalities for separately Lipschitz functionals of composition of random functions ⋮ Stochastic boosting algorithms

Uses Software

• AdaBoost.MH

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Bagging predictors
• Occam's razor
• The weighted majority algorithm
• Heuristics of instability and stabilization in model selection
• A decision-theoretic generalization of on-line learning and an application to boosting
• Predicting a binary sequence almost as well as the optimal biased coin
• Boosting the margin: a new explanation for the effectiveness of voting methods
• Some PAC-Bayesian theorems
• 10.1162/15324430152733133
• How to use expert advice
• Structural risk minimization over data-dependent hierarchies
• 10.1162/153244302760200704
• The context-tree weighting method: basic properties
• Probability Inequalities for Sums of Bounded Random Variables
• A variational principle for invariant odd-dimensional submanifolds of an energy surface for Hamiltonian systems

This page was built for publication: Generalization bounds for averaged classifiers