Online nearest neighbor classification

Sanjoy Dasgupta; Geelon So

Online nearest neighbor classification

Machine Learning 2023-07-04 v1

Authors: Sanjoy Dasgupta , Geelon So

Abstract

We study an instance of online non-parametric classification in the realizable setting. In particular, we consider the classical 1-nearest neighbor algorithm, and show that it achieves sublinear regret - that is, a vanishing mistake rate - against dominated or smoothed adversaries in the realizable setting.

Keywords

online learning online algorithm classification

Cite

@article{arxiv.2307.01170,
  title  = {Online nearest neighbor classification},
  author = {Sanjoy Dasgupta and Geelon So},
  journal= {arXiv preprint arXiv:2307.01170},
  year   = {2023}
}

Related papers

View all related →