Open Access
2022 Binary classification with corrupted labels
Yonghoon Lee, Rina Foygel Barber
Author Affiliations +
Electron. J. Statist. 16(1): 1367-1392 (2022). DOI: 10.1214/22-EJS1987


In a binary classification problem where the goal is to fit an accurate predictor, the presence of corrupted labels in the training data set may create an additional challenge. However, in settings where likelihood maximization is poorly behaved—for example, if positive and negative labels are perfectly separable—then a small fraction of corrupted labels can improve performance by ensuring robustness. In this work, we establish that in such settings, corruption acts as a form of regularization, and we compute precise upper bounds on estimation error in the presence of corruptions. Our results suggest that the presence of corrupted data points is beneficial only up to a small fraction of the total sample, scaling with the square root of the sample size.

Funding Statement

R.F.B. was partially supported by the National Science Foundation via grants DMS-1654076 and DMS-2023109, and by the Office of Naval Research via grant N00014-20-1-2337.


Download Citation

Yonghoon Lee. Rina Foygel Barber. "Binary classification with corrupted labels." Electron. J. Statist. 16 (1) 1367 - 1392, 2022.


Received: 1 June 2021; Published: 2022
First available in Project Euclid: 2 March 2022

MathSciNet: MR4387845
zbMATH: 1493.62390
Digital Object Identifier: 10.1214/22-EJS1987

Primary: 62H30

Keywords: ‎classification‎ , label noise

Vol.16 • No. 1 • 2022
Back to Top