Sparse Regression for Extreme Values

TL;DR

This paper introduces the Extreme Lasso, a new sparse regression method tailored for modeling and selecting features associated with extreme values in high-dimensional data, emphasizing the importance of these values as signals rather than outliers.

Contribution

It proposes a novel $ ext{l}_p$ norm loss-based method for extreme value regression, proves its consistency, and demonstrates its superiority through simulations and real data analysis.

Findings

Extreme Lasso outperforms existing methods in identifying features linked to extreme values.

The $ ext{l}_p$ norm loss emphasizes extreme observations, improving model focus on rare but important signals.

Theoretical analysis confirms the consistency and variable selection properties of the proposed method.

Abstract

We study the problem of selecting features associated with extreme values in high dimensional linear regression. Normally, in linear modeling problems, the presence of abnormal extreme values or outliers is considered an anomaly which should either be removed from the data or remedied using robust regression methods. In many situations, however, the extreme values in regression modeling are not outliers but rather the signals of interest; consider traces from spiking neurons, volatility in finance, or extreme events in climate science, for example. In this paper, we propose a new method for sparse high-dimensional linear regression for extreme values which is motivated by the Subbotin, or generalized normal distribution, which we call the extreme value linear regression model. For our method, we utilize an $\ell_p$ norm loss where $p$ is an even integer greater than two; we demonstrate that this loss increases the weight on extreme values. We prove consistency and variable selection consistency for the extreme value linear regression with a Lasso penalty, which we term the Extreme Lasso, and we also analyze the theoretical impact of extreme value observations on the model parameter estimates using the concept of influence functions. Through simulation studies and a real-world data example, we show that the Extreme Lasso outperforms other methods currently used in the literature for selecting features of interest associated with extreme values in high-dimensional regression.