Outlier Robust and Sparse Estimation of Linear Regression Coefficients
Abstract
We consider outlier-robust and sparse estimation of linear regression coefficients, when the covariates and the noises are contaminated by adversarial outliers and noises are sampled from a heavy-tailed distribution. Our results present sharper error bounds under weaker assumptions than prior studies that share similar interests with this study. Our analysis relies on some sharp concentration inequalities resulting from generic chaining.
Cite
Text
Sasai and Fujisawa. "Outlier Robust and Sparse Estimation of Linear Regression Coefficients." Journal of Machine Learning Research, 2025.Markdown
[Sasai and Fujisawa. "Outlier Robust and Sparse Estimation of Linear Regression Coefficients." Journal of Machine Learning Research, 2025.](https://mlanthology.org/jmlr/2025/sasai2025jmlr-outlier/)BibTeX
@article{sasai2025jmlr-outlier,
title = {{Outlier Robust and Sparse Estimation of Linear Regression Coefficients}},
author = {Sasai, Takeyuki and Fujisawa, Hironori},
journal = {Journal of Machine Learning Research},
year = {2025},
pages = {1-79},
volume = {26},
url = {https://mlanthology.org/jmlr/2025/sasai2025jmlr-outlier/}
}