Near-Exponential Convergence Rates for kNN Classification based on Boltzmann Margin
TL;DR
Boltzmann margin is applied to the analysis of kNN classifiers and establish the first near-exponential convergence rates for kNN classification, which is also the first near-exponential convergence rates for kNN classification.
Abstract
Convergence-rate analysis for classifiers is often conducted under either Tsybakov margin or Massart margin. The former is a relatively weak condition that typically yields polynomial rates, while the latter is substantially stronger but can guarantee exponential rates. In this paper, we introduce a new condition, called Boltzmann margin, that bridges the gap between these two regimes. It is weaker than Massart margin, generally stronger than Tsybakov margin, and can imply many of their properties under suitable conditions. We apply Boltzmann margin to the analysis of kNN classifiers and establish the first near-exponential convergence rates for kNN classification. We also present extensions of the main results and provide numerical evidence supporting the main theoretical implications.
