Plug-in Approach to Active Learning
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.
Cite
Text
Minsker. "Plug-in Approach to Active Learning." Journal of Machine Learning Research, 2012.Markdown
[Minsker. "Plug-in Approach to Active Learning." Journal of Machine Learning Research, 2012.](https://mlanthology.org/jmlr/2012/minsker2012jmlr-plugin/)BibTeX
@article{minsker2012jmlr-plugin,
title = {{Plug-in Approach to Active Learning}},
author = {Minsker, Stanislav},
journal = {Journal of Machine Learning Research},
year = {2012},
pages = {67-90},
volume = {13},
url = {https://mlanthology.org/jmlr/2012/minsker2012jmlr-plugin/}
}