A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers

Abstract

AdaBoost is a well-known algorithm in boosting. Schapire and Singer propose, an extension of AdaBoost, named AdaBoost.MH, for multi-class classification problems. Kégl shows empirically that AdaBoost.MH works better when the classical one-against-all base classifiers are replaced by factorized base classifiers containing a binary classifier and a vote (or code) vector. However, the factorization makes it much more difficult to provide a convergence result for the factorized version of AdaBoost.MH. Then, Kégl raises an open problem in COLT 2014 to look for a convergence result for the factorized AdaBoost.MH. In this work, we resolve this open problem by presenting a convergence result for AdaBoost.MH with factorized multi-class classifiers.

PDF NeurIPS OpenReview Semantic Scholar

Cite

Text

Zou et al. "A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers." Neural Information Processing Systems, 2024. doi:10.52202/079017-2533

Markdown

[Zou et al. "A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers." Neural Information Processing Systems, 2024.](https://mlanthology.org/neurips/2024/zou2024neurips-boostingtype/) doi:10.52202/079017-2533

BibTeX

@inproceedings{zou2024neurips-boostingtype,
  title     = {{A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers}},
  author    = {Zou, Xin and Zhou, Zhengyu and Xu, Jingyuan and Liu, Weiwei},
  booktitle = {Neural Information Processing Systems},
  year      = {2024},
  doi       = {10.52202/079017-2533},
  url       = {https://mlanthology.org/neurips/2024/zou2024neurips-boostingtype/}
}