Importance Weighted Active Learning

Alina Beygelzimer, Sanjoy Dasgupta, John Langford

ICML 2009 pp. 49-56

doi:10.1145/1553374.1553381 /icml/2009/beygelzimer2009icml-importance/

Abstract

We present a practical and statistically consistent scheme for actively learning binary classifiers under general loss functions. Our algorithm uses importance weighting to correct sampling bias, and by controlling the variance, we are able to give rigorous label complexity bounds for the learning process.

PDF ICML Semantic Scholar

Cite

Text

Beygelzimer et al. "Importance Weighted Active Learning." International Conference on Machine Learning, 2009. doi:10.1145/1553374.1553381

Markdown

[Beygelzimer et al. "Importance Weighted Active Learning." International Conference on Machine Learning, 2009.](https://mlanthology.org/icml/2009/beygelzimer2009icml-importance/) doi:10.1145/1553374.1553381

BibTeX

@inproceedings{beygelzimer2009icml-importance,
  title     = {{Importance Weighted Active Learning}},
  author    = {Beygelzimer, Alina and Dasgupta, Sanjoy and Langford, John},
  booktitle = {International Conference on Machine Learning},
  year      = {2009},
  pages     = {49-56},
  doi       = {10.1145/1553374.1553381},
  url       = {https://mlanthology.org/icml/2009/beygelzimer2009icml-importance/}
}