Adversarial robust weighted Huber regression
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916258006433792 |
|---|---|
| author | Sasai, Takeyuki Fujisawa, Hironori |
| author_facet | Sasai, Takeyuki Fujisawa, Hironori |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2102_11120 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Adversarial robust weighted Huber regression Sasai, Takeyuki Fujisawa, Hironori Statistics Theory Machine Learning 62G35, 62G05 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. |
| title | Adversarial robust weighted Huber regression |
| topic | Statistics Theory Machine Learning 62G35, 62G05 |
| url | https://arxiv.org/abs/2102.11120 |