Cellular Tree Classifiers
Machine Learning
2013-06-26 v2 Machine Learning
Statistics Theory
Statistics Theory
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", . 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
@article{arxiv.1301.4679,
title = {Cellular Tree Classifiers},
author = {Gérard Biau and Luc Devroye},
journal= {arXiv preprint arXiv:1301.4679},
year = {2013}
}