Cross-Validation Confidence Intervals for Test Error

Abstract

This work develops central limit theorems for cross-validation and consistent estimators of the asymptotic variance under weak stability conditions on the learning algorithm. Together, these results provide practical, asymptotically-exact confidence intervals for k-fold test error and valid, powerful hypothesis tests of whether one learning algorithm has smaller k-fold test error than another. These results are also the first of their kind for the popular choice of leave-one-out cross-validation. In our experiments with diverse learning algorithms, the resulting intervals and tests outperform the most popular alternative methods from the literature.

Cite

Text

Bayle et al. "Cross-Validation Confidence Intervals for Test Error." Neural Information Processing Systems, 2020.

Markdown

[Bayle et al. "Cross-Validation Confidence Intervals for Test Error." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/bayle2020neurips-crossvalidation/)

BibTeX

@inproceedings{bayle2020neurips-crossvalidation,
  title     = {{Cross-Validation Confidence Intervals for Test Error}},
  author    = {Bayle, Pierre and Bayle, Alexandre and Janson, Lucas and Mackey, Lester W.},
  booktitle = {Neural Information Processing Systems},
  year      = {2020},
  url       = {https://mlanthology.org/neurips/2020/bayle2020neurips-crossvalidation/}
}