Active Learning with a Drifting Distribution
Abstract
We study the problem of active learning in a stream-based setting, allowing the distribution of the examples to change over time. We prove upper bounds on the number of prediction mistakes and number of label requests for established disagreement-based active learning algorithms, both in the realizable case and under Tsybakov noise. We further prove minimax lower bounds for this problem.
Cite
Text
Yang. "Active Learning with a Drifting Distribution." Neural Information Processing Systems, 2011.Markdown
[Yang. "Active Learning with a Drifting Distribution." Neural Information Processing Systems, 2011.](https://mlanthology.org/neurips/2011/yang2011neurips-active/)BibTeX
@inproceedings{yang2011neurips-active,
title = {{Active Learning with a Drifting Distribution}},
author = {Yang, Liu},
booktitle = {Neural Information Processing Systems},
year = {2011},
pages = {2079-2087},
url = {https://mlanthology.org/neurips/2011/yang2011neurips-active/}
}