共 50 条
Robust Inference for High-Dimensional Linear Models via Residual Randomization
被引:0
|作者:
Wang, Y. Samuel
[1
]
Lee, Si Kai
[1
]
Toulis, Panos
[1
]
Kolar, Mladen
[1
]
机构:
[1] Univ Chicago, Booth Sch Business, Chicago, IL 60637 USA
来源:
关键词:
CONFIDENCE-INTERVALS;
LASSO;
D O I:
暂无
中图分类号:
TP18 [人工智能理论];
学科分类号:
081104 ;
0812 ;
0835 ;
1405 ;
摘要:
We propose a residual randomization procedure designed for robust Lasso-based inference in the high-dimensional setting. Compared to earlier work that focuses on sub-Gaussian errors, the proposed procedure is designed to work robustly in settings that also include heavy-tailed covariates and errors. Moreover, our procedure can be valid under clustered errors, which is important in practice, but has been largely overlooked by earlier work. Through extensive simulations, we illustrate our method's wider range of applicability as suggested by theory. In particular, we show that our method outperforms state-of-art methods in challenging, yet more realistic, settings where the distribution of covariates is heavy-tailed or the sample size is small, while it remains competitive in standard, "well behaved" settings previously studied in the literature.
引用
收藏
页码:7818 / 7828
页数:11
相关论文