Generalization Bounds for Voting Classifiers Based on Sparsity and Clustering
Abstract
We prove new margin type bounds on the generalization error of voting classifiers that take into account the sparsity of weights and certain measures of clustering of weak classifiers in the convex combination. We also present experimental results to illustrate the behavior of the parameters of interest for several data sets.
Cite
Text
Koltchinskii et al. "Generalization Bounds for Voting Classifiers Based on Sparsity and Clustering." Annual Conference on Computational Learning Theory, 2003. doi:10.1007/978-3-540-45167-9_36Markdown
[Koltchinskii et al. "Generalization Bounds for Voting Classifiers Based on Sparsity and Clustering." Annual Conference on Computational Learning Theory, 2003.](https://mlanthology.org/colt/2003/koltchinskii2003colt-generalization/) doi:10.1007/978-3-540-45167-9_36BibTeX
@inproceedings{koltchinskii2003colt-generalization,
title = {{Generalization Bounds for Voting Classifiers Based on Sparsity and Clustering}},
author = {Koltchinskii, Vladimir and Panchenko, Dmitry and Andonova, Savina},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2003},
pages = {492-505},
doi = {10.1007/978-3-540-45167-9_36},
url = {https://mlanthology.org/colt/2003/koltchinskii2003colt-generalization/}
}