Teaching Dimension and the Complexity of Active Learning

Abstract

We study the label complexity of pool-based active learning in the PAC model with noise. Taking inspiration from extant literature on Exact learning with membership queries, we derive upper and lower bounds on the label complexity in terms of generalizations of extended teaching dimension . Among the contributions of this work is the first nontrivial general upper bound on label complexity in the presence of persistent classification noise.

Cite

Text

Hanneke. "Teaching Dimension and the Complexity of Active Learning." Annual Conference on Computational Learning Theory, 2007. doi:10.1007/978-3-540-72927-3_7

Markdown

[Hanneke. "Teaching Dimension and the Complexity of Active Learning." Annual Conference on Computational Learning Theory, 2007.](https://mlanthology.org/colt/2007/hanneke2007colt-teaching/) doi:10.1007/978-3-540-72927-3_7

BibTeX

@inproceedings{hanneke2007colt-teaching,
  title     = {{Teaching Dimension and the Complexity of Active Learning}},
  author    = {Hanneke, Steve},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2007},
  pages     = {66-81},
  doi       = {10.1007/978-3-540-72927-3_7},
  url       = {https://mlanthology.org/colt/2007/hanneke2007colt-teaching/}
}