K-NN active learning under local smoothness assumption

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.

arXiv commentarXiv admin note: substantial text overlap with arXiv:1902.03055

References in corpus (10)

• On the Complexity of Best Arm Identification in Multi-Armed Bandit Models
• Fast learning rates for plug-in classifiers
• Risk bounds for statistical learning
• Empirical Bernstein Bounds and Sample Variance Penalization
• Rates of Convergence for Nearest Neighbor Classification
• k-NN Regression Adapts to Local Intrinsic Dimension
• Active Nearest-Neighbor Learning in Metric Spaces
• Minimax rates for cost-sensitive learning on manifolds with approximate nearest neighbours
• Adaptivity to Noise Parameters in Nonparametric Active Learning
• Five Proofs of Chernoff's Bound with Applications

Cited by in corpus (1)

• Nonparametric adaptive active learning under local smoothness condition