Nonparametric adaptive active learning under local smoothness condition

TL;DR

This paper introduces a new adaptive active learning algorithm for nonparametric data that works under minimal assumptions, achieving near-optimal convergence rates and applicable to a broad class of distributions.

Contribution

It proposes a novel algorithm that adapts to unknown parameters in nonparametric active learning, broadening applicability beyond previous methods.

Findings

Achieves minimax rate of convergence

Works under more general distribution assumptions

Performs nearly as well as non-adaptive algorithms

Abstract

Active learning is typically used to label data, when the labeling process is expensive. Several active learning algorithms have been theoretically proved to perform better than their passive counterpart. However, these algorithms rely on some assumptions, which themselves contain some specific parameters. This paper adresses the problem of adaptive active learning in a nonparametric setting with minimal assumptions. We present a novel algorithm that is valid under more general assumptions than the previously known algorithms, and that can moreover adapt to the parameters used in these assumptions. This allows us to work with a larger class of distributions, thereby avoiding to exclude important densities like gaussians. Our algorithm achieves a minimax rate of convergence, and therefore performs almost as well as the best known non-adaptive algorithms.