English

A Nearest Neighbor Characterization of Lebesgue Points in Metric Measure Spaces

Machine Learning 2021-01-13 v4 Probability Machine Learning

Abstract

The property of almost every point being a Lebesgue point has proven to be crucial for the consistency of several classification algorithms based on nearest neighbors. We characterize Lebesgue points in terms of a 1-Nearest Neighbor regression algorithm for pointwise estimation, fleshing out the role played by tie-breaking rules in the corresponding convergence problem. We then give an application of our results, proving the convergence of the risk of a large class of 1-Nearest Neighbor classification algorithms in general metric spaces where almost every point is a Lebesgue point.

Keywords

Cite

@article{arxiv.2007.03937,
  title  = {A Nearest Neighbor Characterization of Lebesgue Points in Metric Measure Spaces},
  author = {Tommaso Cesari and Roberto Colomboni},
  journal= {arXiv preprint arXiv:2007.03937},
  year   = {2021}
}