Back to Search
Start Over
Adversarial robust weighted Huber regression
- Publication Year :
- 2021
-
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 $L$-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.<br />Comment: The case of sparse coefficients is investigated in arXiv:2208.11592. This manuscript will not be submitted for publications
- Subjects :
- Mathematics - Statistics Theory
Statistics - Machine Learning
62G35, 62G05
Subjects
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2102.11120
- Document Type :
- Working Paper