Electronic Journal of Statistics

Corrigendum to “Classification with asymmetric label noise: Consistency and maximal denoising”

Gilles Blanchard and Clayton Scott

Full-text: Open access

Abstract

We point out a flaw in Lemma 15 of [1]. We also indicate how the main results of that section are still valid using a modified argument.

Article information

Source
Electron. J. Statist., Volume 12, Number 1 (2018), 1779-1781.

Dates
Received: March 2018
First available in Project Euclid: 9 June 2018

Permanent link to this document
https://projecteuclid.org/euclid.ejs/1528509712

Digital Object Identifier
doi:10.1214/18-EJS1422

Rights
Creative Commons Attribution 4.0 International License.

Citation

Blanchard, Gilles; Scott, Clayton. Corrigendum to “Classification with asymmetric label noise: Consistency and maximal denoising”. Electron. J. Statist. 12 (2018), no. 1, 1779--1781. doi:10.1214/18-EJS1422. https://projecteuclid.org/euclid.ejs/1528509712


Export citation

References

  • [1] G. Blanchard, M. Flaska, G. Handy, S. Pozzi, and C. Scott. Classification with asymmetric label noise: Consistency and maximal denoising., Electronic Journal of Statistics, 10 :2780–2824, 2016.
  • [2] N. Natarajan, I. S. Dhillon, P. Ravikumar, and A. Tewari. Learning with noisy labels. In, Advances in Neural Information Processing Systems 26, 2013.
  • [3] N. Natarajan, I. S. Dhillon, P. Ravikumar, and A. Tewari. Cost-sensitive learning with noisy labels., Journal of Machine Learning Research, 18(155):1–33, 2018. URL http://jmlr.org/papers/v18/15-226.html.

See also

  • Related item: Blanchard, Gilles; Flaska, Marek; Handy, Gregory; Pozzi, Sara; Scott, Clayton. Classification with asymmetric label noise: Consistency and maximal denoising. Electron. J. Statist. 10 (2016), no. 2, 2780–2824.