Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Optimal ridge regularization revisited

About

We consider $L^2$-regularized linear (ridge) regression over a finite data sample $X$ with bounded covariance and linear prediction targets $y$ with additive isotropic noise of finite variance. We present an iterative procedure to compute the optimal regularization strength numerically from the generative parameters in the fixed-$X$ setting and prove its convergence at limited noise levels. Our experimental evaluation over synthetic data shows that the proposed procedure combined with sample-based parameter estimates attains near-optimal random-$X$ generalization across a wide range of sample sizes, aspect ratios, and noise levels, at an added computational cost equivalent to one preliminary ridge regression in the underparameterized regime and two in the overparameterized case.

Jack Timmermans, Sergio A. Alvarez• 2026

Related benchmarks

TaskDatasetResultRank
Out-of-sample random-X regressionSpiked covariance model d/N = 0.9, noise = 1 synthetic (out-of-sample)
Median MSE0.97
196
RegressionSynthetic Spiked Covariance d/N = 0.9 (out-of-sample)
Median log10 MSE-2.83
108
Out-of-sample Mean Squared Error EstimationSpiked covariance model N = 200
Median OOS Random-X MSE1.08
36
Ridge RegressionSpiked covariance model N=20 synthetic
Median Out-of-Sample MSE1.14
5
Ridge RegressionSpiked covariance model synthetic (N=100)
Median Out-of-Sample MSE1.15
5
Ridge RegressionSpiked covariance model N=500 synthetic
Median Out-of-Sample MSE1.15
5
Showing 6 of 6 rows

Other info

Follow for update