A Theory of Multiclass Boosting
Abstract
Boosting combines weak classifiers to form highly accurate predictors. Although the case of binary classification is well understood, in the multiclass setting, the "correct" requirements on the weak classifier, or the notion of the most efficient boosting algorithms are missing. In this paper, we create a broad and general framework, within which we make precise and identify the optimal requirements on the weak-classifier, as well as design the most effective, in a certain sense, boosting algorithms that assume such requirements.
Cite
Text
Mukherjee and Schapire. "A Theory of Multiclass Boosting." Neural Information Processing Systems, 2010.Markdown
[Mukherjee and Schapire. "A Theory of Multiclass Boosting." Neural Information Processing Systems, 2010.](https://mlanthology.org/neurips/2010/mukherjee2010neurips-theory/)BibTeX
@inproceedings{mukherjee2010neurips-theory,
title = {{A Theory of Multiclass Boosting}},
author = {Mukherjee, Indraneel and Schapire, Robert E.},
booktitle = {Neural Information Processing Systems},
year = {2010},
pages = {1714-1722},
url = {https://mlanthology.org/neurips/2010/mukherjee2010neurips-theory/}
}