Adversarial robust weighted Huber regression
Statistics Theory
2024-05-27 v4 Machine Learning
Statistics Theory
Abstract
We consider a robust estimation of linear regression coefficients. In this note, we focus on the case where the covariates are sampled from an -subGaussian distribution with unknown covariance, the noises are sampled from a distribution with a bounded absolute moment and both covariates and noises may be contaminated by an adversary. We derive an estimation error bound, which depends on the stable rank and the condition number of the covariance matrix of covariates with a polynomial computational complexity of estimation.
Cite
@article{arxiv.2102.11120,
title = {Adversarial robust weighted Huber regression},
author = {Takeyuki Sasai and Hironori Fujisawa},
journal= {arXiv preprint arXiv:2102.11120},
year = {2024}
}
Comments
The case of sparse coefficients is investigated in arXiv:2208.11592. This manuscript will not be submitted for publications