Plug-in Approach to Active Learning

2011/04/07 by Stanislav Minsker, Minsker, Stanislav · 1 citation
Computer Science · Mathematics · #Machine Learning and Algorithms #Algorithms and Data Compression #Statistical Methods and Inference

paper · pdf · doi:10.48550/arxiv.1104.1450

Abstract

We present a new active learning algorithm based on nonparametric estimators of the regression function. Our investigation provides probabilistic bounds for the rates of convergence of the generalization error achievable by proposed method over a broad class of underlying distributions. We also prove minimax lower bounds which show that the obtained rates are almost tight.

Cited by

• Active Learning via Regression Beyond Realizability

Related

• Nonparametric adaptive active learning under local smoothness condition
• Adaptivity to Noise Parameters in Nonparametric Active Learning
• Convergence Rates of Active Learning for Maximum Likelihood Estimation
• Optimal Sampling Density for Nonparametric Regression
• K-NN active learning under local smoothness assumption