Back to Search
Start Over
Outlier Robust and Sparse Estimation of Linear Regression Coefficients
- Publication Year :
- 2022
-
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.
- Subjects :
- Mathematics - Statistics Theory
Statistics - Machine Learning
62J07, 62F35
Subjects
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2208.11592
- Document Type :
- Working Paper