Skip to Main content Skip to Navigation
Journal articles

Optimal Rates for Nonparametric F-Score Binary Classification via Post-Processing

Evgenii Chzhen 1, 2 
1 CELESTE - Statistique mathématique et apprentissage
Inria Saclay - Ile de France, LMO - Laboratoire de Mathématiques d'Orsay
Abstract : This work studies the problem of binary classification with the F-score as the performance measure. We propose a post-processing algorithm for this problem which fits a threshold for any score base classifier to yield high F-score. The post-processing step involves only unlabeled data and can be performed in logarithmic time. We derive a general finite sample post-processing bound for the proposed procedure and show that the procedure is minimax rate optimal, when the underlying distribution satisfies classical nonparametric assumptions. This result improves upon previously known rates for the F-score classification and bridges the gap between standard classification risk and the F-score. Finally, we discuss the generalization of this approach to the set-valued classification.
Document type :
Journal articles
Complete list of metadata

Cited literature [26 references]  Display  Hide  Download
Contributor : Evgenii Chzhen Connect in order to contact the contributor
Submitted on : Wednesday, May 8, 2019 - 12:40:53 AM
Last modification on : Thursday, September 29, 2022 - 2:21:15 PM
Long-term archiving on: : Thursday, October 10, 2019 - 11:58:46 AM


Files produced by the author(s)



Evgenii Chzhen. Optimal Rates for Nonparametric F-Score Binary Classification via Post-Processing. Mathematical Methods of Statistics, Allerton Press, Springer (link), 2021, ⟨10.3103/S1066530720020027⟩. ⟨hal-02123314⟩



Record views


Files downloads