Diameter-Based Active Learning
Abstract
To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index. We provide, for the first time, an efficient algorithm that is able to realize this upper bound, and we empirically demonstrate its good performance.
Cite
Text
Tosh and Dasgupta. "Diameter-Based Active Learning." International Conference on Machine Learning, 2017.Markdown
[Tosh and Dasgupta. "Diameter-Based Active Learning." International Conference on Machine Learning, 2017.](https://mlanthology.org/icml/2017/tosh2017icml-diameterbased/)BibTeX
@inproceedings{tosh2017icml-diameterbased,
title = {{Diameter-Based Active Learning}},
author = {Tosh, Christopher and Dasgupta, Sanjoy},
booktitle = {International Conference on Machine Learning},
year = {2017},
pages = {3444-3452},
volume = {70},
url = {https://mlanthology.org/icml/2017/tosh2017icml-diameterbased/}
}