Robust Logistic Regression and Classification
Abstract
We consider logistic regression with arbitrary outliers in the covariate matrix. We propose a new robust logistic regression algorithm, called RoLR, that estimates the parameter through a simple linear programming procedure. We prove that RoLR is robust to a constant fraction of adversarial outliers. To the best of our knowledge, this is the first result on estimating logistic regression model when the covariate matrix is corrupted with any performance guarantees. Besides regression, we apply RoLR to solving binary classification problems where a fraction of training samples are corrupted.
Cite
Text
Feng et al. "Robust Logistic Regression and Classification." Neural Information Processing Systems, 2014.Markdown
[Feng et al. "Robust Logistic Regression and Classification." Neural Information Processing Systems, 2014.](https://mlanthology.org/neurips/2014/feng2014neurips-robust/)BibTeX
@inproceedings{feng2014neurips-robust,
title = {{Robust Logistic Regression and Classification}},
author = {Feng, Jiashi and Xu, Huan and Mannor, Shie and Yan, Shuicheng},
booktitle = {Neural Information Processing Systems},
year = {2014},
pages = {253-261},
url = {https://mlanthology.org/neurips/2014/feng2014neurips-robust/}
}