Regularity Properties for Sparse Regression

TL;DR

This paper investigates the computational complexity of verifying conditions essential for sparse regression, proving NP-hardness for many, but also identifying a more practical, probabilistically-robust condition called $\

Contribution

It proves NP-hardness of checking key sparse regression conditions and analyzes the practical relevance of $\

Findings

NP-hardness of verifying restricted eigenvalue and compatibility conditions

$\

paper_type":"theoretical"} }

Abstract

Statistical and machine learning theory has developed several conditions ensuring that popular estimators such as the Lasso or the Dantzig selector perform well in high-dimensional sparse regression, including the restricted eigenvalue, compatibility, and $\ell_q$ sensitivity properties. However, some of the central aspects of these conditions are not well understood. For instance, it is unknown if these conditions can be checked efficiently on any given data set. This is problematic, because they are at the core of the theory of sparse regression. Here we provide a rigorous proof that these conditions are NP-hard to check. This shows that the conditions are computationally infeasible to verify, and raises some questions about their practical applications. However, by taking an average-case perspective instead of the worst-case view of NP-hardness, we show that a particular condition, $\ell_q$ sensitivity, has certain desirable properties. This condition is weaker and more general than the others. We show that it holds with high probability in models where the parent population is well behaved, and that it is robust to certain data processing steps. These results are desirable, as they provide guidance about when the condition, and more generally the theory of sparse regression, may be relevant in the analysis of high-dimensional correlated observational data.