On the Foundations of Noise-Free Selective Classification

Abstract

We consider selective classification, a term we adopt here to refer to 'classification with a reject option.' The essence in selective classification is to trade-off classifier coverage for higher accuracy. We term this trade-off the risk-coverage (RC) trade-off. Our main objective is to characterize this trade-off and to construct algorithms that can optimally or near optimally achieve the best possible trade-offs in a controlled manner. For noise-free models we present in this paper a thorough analysis of selective classification including characterizations of RC trade-offs in various interesting settings.

Cite

Text

El-Yaniv and Wiener. "On the Foundations of Noise-Free Selective Classification." Journal of Machine Learning Research, 2010.

Markdown

[El-Yaniv and Wiener. "On the Foundations of Noise-Free Selective Classification." Journal of Machine Learning Research, 2010.](https://mlanthology.org/jmlr/2010/elyaniv2010jmlr-foundations/)

BibTeX

@article{elyaniv2010jmlr-foundations,
  title     = {{On the Foundations of Noise-Free Selective Classification}},
  author    = {El-Yaniv, Ran and Wiener, Yair},
  journal   = {Journal of Machine Learning Research},
  year      = {2010},
  pages     = {1605-1641},
  volume    = {11},
  url       = {https://mlanthology.org/jmlr/2010/elyaniv2010jmlr-foundations/}
}