ML Anthology

Negative Results for Active Learning with Convex Losses

Steve Hanneke, Liu Yang
AISTATS 2010 pp. 321-325
/aistats/2010/hanneke2010aistats-negative/

Abstract

We study the problem of active learning with convex loss functions. We prove that even under bounded noise constraints, the minimax rates for proper active learning are often no better than passive learning.

PDF AISTATS Semantic Scholar

Cite

Text

Hanneke and Yang. "Negative Results for Active Learning with Convex Losses." Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010.

Markdown

[Hanneke and Yang. "Negative Results for Active Learning with Convex Losses." Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010.](https://mlanthology.org/aistats/2010/hanneke2010aistats-negative/)

BibTeX

@inproceedings{hanneke2010aistats-negative,
  title     = {{Negative Results for Active Learning with Convex Losses}},
  author    = {Hanneke, Steve and Yang, Liu},
  booktitle = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics},
  year      = {2010},
  pages     = {321-325},
  volume    = {9},
  url       = {https://mlanthology.org/aistats/2010/hanneke2010aistats-negative/}
}