@misc{bayle2020cross-validation, author = {Bayle, Pierre and Bayle, Alexandre and Janson, Lucas and Mackey, Lester}, title = {Cross-validation Confidence Intervals for Test Error}, howpublished = {ArXiv}, year = {2020}, month = {July}, abstract = {This work develops central limit theorems for cross-validation and consistent estimators of its 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 real-data experiments with diverse learning algorithms, the resulting intervals and tests outperform the most popular alternative methods from the literature.}, url = {http://approjects.co.za/?big=en-us/research/publication/cross-validation-confidence-intervals-for-test-error/}, }