Analysis of a Greedy Active Learning Strategy

Abstract

We abstract out the core search problem of active learning schemes, to better understand the extent to which adaptive labeling can improve sam- ple complexity. We give various upper and lower bounds on the number of labels which need to be queried, and we prove that a popular greedy active learning rule is approximately as good as any other strategy for minimizing this number of labels.

Cite

Text

Dasgupta. "Analysis of a Greedy Active Learning Strategy." Neural Information Processing Systems, 2004.

Markdown

[Dasgupta. "Analysis of a Greedy Active Learning Strategy." Neural Information Processing Systems, 2004.](https://mlanthology.org/neurips/2004/dasgupta2004neurips-analysis/)

BibTeX

@inproceedings{dasgupta2004neurips-analysis,
  title     = {{Analysis of a Greedy Active Learning Strategy}},
  author    = {Dasgupta, Sanjoy},
  booktitle = {Neural Information Processing Systems},
  year      = {2004},
  pages     = {337-344},
  url       = {https://mlanthology.org/neurips/2004/dasgupta2004neurips-analysis/}
}