Implicit vs. explicit regularization for high-dimensional gradient descent

Abstract

In this paper we investigate the generalization error of gradient descent (GD) applied to an $\ell_2$-regularized OLS objective function in the linear model. Based on our analysis we develop new methodology for computationally tractable and statistically efficient linear prediction in a high-dimensional and massive data scenario (large-$n$, large-$p$). Our results are based on the surprising observation that the generalization error of optimally tuned regularized gradient descent approaches that of an optimal benchmark procedure $monotonically$ in the iteration number $t$. On the other hand standard GD for OLS (without explicit regularization) can achieve the benchmark only in degenerate cases. This shows that (optimal) explicit regularization can be nearly statistically efficient (for large $t$) whereas implicit regularization by (optimal) early stopping can not. To complete our methodology, we provide a fully data driven and computationally tractable choice of the $\ell_2$ regularization parameter $\lambda$ that is computationally cheaper than cross-validation. On this way, we follow and extend ideas of Dicker (2014) to the non-gaussian case, which requires new results on high-dimensional sample covariance matrices that might be of independent interest.