Active Learning Using Smooth Relative Regret Approximations with Applications
Abstract
The disagreement coefficient of Hanneke has become a central data independent invariant in proving active learning rates. It has been shown in various ways that a concept class with low complexity together with a bound on the disagreement coefficient at an optimal solution allows active learning rates that are superior to passive learning ones.
Cite
Text
Ailon et al. "Active Learning Using Smooth Relative Regret Approximations with Applications." Journal of Machine Learning Research, 2014.Markdown
[Ailon et al. "Active Learning Using Smooth Relative Regret Approximations with Applications." Journal of Machine Learning Research, 2014.](https://mlanthology.org/jmlr/2014/ailon2014jmlr-active/)BibTeX
@article{ailon2014jmlr-active,
title = {{Active Learning Using Smooth Relative Regret Approximations with Applications}},
author = {Ailon, Nir and Begleiter, Ron and Ezra, Esther},
journal = {Journal of Machine Learning Research},
year = {2014},
pages = {885-920},
volume = {15},
url = {https://mlanthology.org/jmlr/2014/ailon2014jmlr-active/}
}