Escaping the Curse of Dimensionality with a Tree-Based Regressor

Abstract

We present the first tree-based regressor whose convergence rate depends only on the intrinsic dimension of the data, namely its Assouad dimension. The regressor uses the RPtree partitioning procedure, a simple randomized variant of k-d trees.

Cite

Text

Kpotufe. "Escaping the Curse of Dimensionality with a Tree-Based Regressor." Annual Conference on Computational Learning Theory, 2009.

Markdown

[Kpotufe. "Escaping the Curse of Dimensionality with a Tree-Based Regressor." Annual Conference on Computational Learning Theory, 2009.](https://mlanthology.org/colt/2009/kpotufe2009colt-escaping/)

BibTeX

@inproceedings{kpotufe2009colt-escaping,
  title     = {{Escaping the Curse of Dimensionality with a Tree-Based Regressor}},
  author    = {Kpotufe, Samory},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2009},
  url       = {https://mlanthology.org/colt/2009/kpotufe2009colt-escaping/}
}