Online nearest neighbor classification

07/03/2023

∙

by   Sanjoy Dasgupta, et al.

∙

0

∙

share

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.