On the existence of linear weak learners and applications to boosting

Machine Learning

Volumn 48, Issue 1-3, 2002, Pages 219-251

  Mannor, Shie ^a   Meir, Ron ^a  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

Author keywords

Boosting; Geometric discrepancy; Weak learner

Indexed keywords

BOUNDARY CONDITIONS; COMPUTATIONAL GEOMETRY; ITERATIVE METHODS; LEARNING ALGORITHMS; PROBLEM SOLVING;

BOOSTING; GEOMETRIC DISCREPANCY; LINEAR WEAK LEARNERS;

LEARNING SYSTEMS;

EID: 0036643066     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1013959922467     Document Type: Article

References (33)

1. Generalized sums of distances
2. Geometric methods in the study of irregularities of distribution
3. Principles of a new method in the study of irregularities of distribution
4. The effect of dimension on certain geometric problems of irregularities of distribution
5. On the hardness of learning with neural networks
6. Bagging predictors
7. Boosting a weak learning algorithm by majority
8. Experiments with a new boosting algorithm
9. Game theory, on-line prediction and boosting
10. Additive logistic regression: A statistical view of boosting
11. The densest hemisphere problem
12. Hierarchical mixtures of experts and the EM algorithm
13. On the boosting ability of top-down decision tree learning algorithms
14. Some new bounds on the generalization error of combined classifiers
15. Functional gradient techniques for combining hypotheses
16. Tight upper bound on the discrepancy of half-spaces
17. Localized boosting
18. Weak learners and improved rates of convergence in boosting
19. Cambridge, England: Cambridge University Press
20. On certain metric spaces arising from euclidean spaces by change of metric and their embedding into hilbert space
21. The strength of weak learnability
22. Boosting the margin: A new explanation for the effectiveness of voting methods
23. Improved boosting algorithms using confidence-rated predictions
24. Estimation of dependences based on empirical data
25. On the uniform convergence of relative frequencies of events to probabilities