Cellular Tree Classifiers

Abstract

The cellular tree classifier model addresses a fundamental problem in the design of classifiers for a parallel or distributed computing world: Given a data set, is it sufficient to apply a majority rule for classification, or shall one split the data into two or more parts and send each part to a potentially different computer (or cell) for further processing? At first sight, it seems impossible to define with this paradigm a consistent classifier as no cell knows the "original data size", $n$. However, we show that this is not so by exhibiting two different consistent classifiers. The consistency is universal but is only shown for distributions with nonatomic marginals.

Cite

Text

Biau and Devroye. "Cellular Tree Classifiers." International Conference on Algorithmic Learning Theory, 2014. doi:10.1007/978-3-319-11662-4_2

Markdown

[Biau and Devroye. "Cellular Tree Classifiers." International Conference on Algorithmic Learning Theory, 2014.](https://mlanthology.org/alt/2014/biau2014alt-cellular/) doi:10.1007/978-3-319-11662-4_2

BibTeX

@inproceedings{biau2014alt-cellular,
  title     = {{Cellular Tree Classifiers}},
  author    = {Biau, Gérard and Devroye, Luc},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2014},
  pages     = {8-17},
  doi       = {10.1007/978-3-319-11662-4_2},
  url       = {https://mlanthology.org/alt/2014/biau2014alt-cellular/}
}