K-NN active learning under local smoothness assumption

TL;DR

This paper introduces a new active learning algorithm for k-nearest neighbors that leverages a local smoothness assumption, achieving faster convergence rates without relying on strong density assumptions.

Contribution

The paper proposes a novel active learning method under a local smoothness assumption tailored for k-NN, improving convergence rates over passive learning and avoiding strict density requirements.

Findings

Achieves better convergence rates than passive learning.

Operates without assuming the existence of a density function.

Utilizes a local smoothness assumption related to the marginal distribution.

Abstract

There is a large body of work on convergence rates either in passive or active learning. Here we first outline some of the main results that have been obtained, more specifically in a nonparametric setting under assumptions about the smoothness of the regression function (or the boundary between classes) and the margin noise. We discuss the relative merits of these underlying assumptions by putting active learning in perspective with recent work on passive learning. We design an active learning algorithm with a rate of convergence better than in passive learning, using a particular smoothness assumption customized for k-nearest neighbors. Unlike previous active learning algorithms, we use a smoothness assumption that provides a dependence on the marginal distribution of the instance space. Additionally, our algorithm avoids the strong density assumption that supposes the existence of the density function of the marginal distribution of the instance space and is therefore more generally applicable.