Plug-in approach to active learning

Authors:
Stanislav Minsker
Affiliations:
School of Mathematics, Georgia Institute of Technology, Atlanta, GA
Venue:
The Journal of Machine Learning Research
Year:
2012

Citing 4
Cited 0

Agnostic active learning

Journal of Computer and System Sciences
Introduction to Nonparametric Estimation

Introduction to Nonparametric Estimation
Rademacher Complexities and Bounding the Excess Risk in Active Learning

The Journal of Machine Learning Research
Minimax Bounds for Active Learning

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

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.