Bounding the generalization error of convex combinations of classifiers: balancing the dimensionality and the margins
Open Access
- 1 January 2003
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Applied Probability
- Vol. 13 (1)
- https://doi.org/10.1214/aoap/1042765667
Abstract
No abstract availableThis publication has 21 references indexed in Scilit:
- Bounds on margin distributions inBlearningBproblemsAnnales de l'Institut Henri Poincaré, Probabilités et Statistiques, 2003
- Empirical Margin Distributions and Bounding the Generalization Error of Combined ClassifiersThe Annals of Statistics, 2002
- Rademacher penalties and structural risk minimizationIEEE Transactions on Information Theory, 2001
- About the constants in Talagrand's concentration inequalities for empirical processesThe Annals of Probability, 2000
- Boosting the margin: a new explanation for the effectiveness of voting methodsThe Annals of Statistics, 1998
- Arcing classifier (with discussion and a rejoinder by the author)The Annals of Statistics, 1998
- The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the networkIEEE Transactions on Information Theory, 1998
- Efficient algorithms for function approximation with piecewise linear sigmoidal networksIEEE Transactions on Neural Networks, 1998
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- Support-vector networksMachine Learning, 1995