Average-Case Active Learning with Costs
Abstract
We analyze the expected cost of a greedy active learning algorithm. Our analysis extends previous work to a more general setting in which different queries have different costs. Moreover, queries may have more than two possible responses and the distribution over hypotheses may be non uniform. Specific applications include active learning with label costs, active learning for multiclass and partial label queries, and batch mode active learning. We also discuss an approximate version of interest when there are very many queries.
Cite
Text
Guillory and Bilmes. "Average-Case Active Learning with Costs." International Conference on Algorithmic Learning Theory, 2009. doi:10.1007/978-3-642-04414-4_15Markdown
[Guillory and Bilmes. "Average-Case Active Learning with Costs." International Conference on Algorithmic Learning Theory, 2009.](https://mlanthology.org/alt/2009/guillory2009alt-averagecase/) doi:10.1007/978-3-642-04414-4_15BibTeX
@inproceedings{guillory2009alt-averagecase,
title = {{Average-Case Active Learning with Costs}},
author = {Guillory, Andrew and Bilmes, Jeff A.},
booktitle = {International Conference on Algorithmic Learning Theory},
year = {2009},
pages = {141-155},
doi = {10.1007/978-3-642-04414-4_15},
url = {https://mlanthology.org/alt/2009/guillory2009alt-averagecase/}
}