ML Anthology

A Simpler Analysis of the Multi-Way Branching Decision Tree Boosting Algorithm

Kohei Hatano
ALT 2001 pp. 77-91
doi:10.1007/3-540-45583-3_8 /alt/2001/hatano2001alt-simpler/

Abstract

We improve the analysis of the decision tree boosting algorithm proposed by Mansour and McAllester. For binary classification problems, the algorithm of Mansour and McAllester constructs a multiway branching decision tree using a set of multi-class hypotheses. Mansour and McAllester proved that it works under certain conditions. We give a much simpler analysis of the algorithm and simplify the conditions. From this simplification, we can provide a simpler algorithm, for which no prior knowledge on the quality of weak hypotheses is necessary.

PDF ALT Semantic Scholar

Cite

Text

Hatano. "A Simpler Analysis of the Multi-Way Branching Decision Tree Boosting Algorithm." International Conference on Algorithmic Learning Theory, 2001. doi:10.1007/3-540-45583-3_8

Markdown

[Hatano. "A Simpler Analysis of the Multi-Way Branching Decision Tree Boosting Algorithm." International Conference on Algorithmic Learning Theory, 2001.](https://mlanthology.org/alt/2001/hatano2001alt-simpler/) doi:10.1007/3-540-45583-3_8

BibTeX

@inproceedings{hatano2001alt-simpler,
  title     = {{A Simpler Analysis of the Multi-Way Branching Decision Tree Boosting Algorithm}},
  author    = {Hatano, Kohei},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2001},
  pages     = {77-91},
  doi       = {10.1007/3-540-45583-3_8},
  url       = {https://mlanthology.org/alt/2001/hatano2001alt-simpler/}
}