Abstract
Random matrix theory has become a widely useful tool in high-dimensional statistics and theoretical machine learning. However, random matrix theory is largely focused on the proportional asymptotics in which the number of columns grows proportionally to the number of rows of the data matrix. This is not always the most natural setting in statistics where columns correspond to covariates and rows to samples.
With the objective to move beyond the proportional asymptotics, we revisit ridge regression (-penalized least squares) on i.i.d. data , , where is a feature vector and is a response. We allow the feature vector to be high-dimensional, or even infinite-dimensional, in which case it belongs to a separable Hilbert space, and assume either to have i.i.d. entries, or to satisfy a certain convex concentration property.
Within this setting, we establish nonasymptotic bounds that approximate the bias and variance of ridge regression in terms of the bias and variance of an “equivalent” sequence model (a regression model with diagonal design matrix). The approximation is up to multiplicative factors bounded by for some explicitly small Δ.
Previously, such an approximation result was known only in the proportional regime and only up to additive errors: in particular, it did not allow to characterize the behavior of the excess risk when this converges to 0. Our general theory recovers earlier results in the proportional regime (with better error rates). As a new application, we obtain a completely explicit and sharp characterization of ridge regression for Hilbert covariates with regularly varying spectrum. Finally, we analyze the overparametrized near-interpolation setting and obtain sharp “benign overfitting” guarantees.
Funding Statement
This work was supported by the NSF through award DMS-2031883, the Simons Foundation through Award 814639 for the Collaboration on the Theoretical Foundations of Deep Learning, NSF Grant CCF-2006489, the ONR grant N00014-18-1-2729, and a grant from Eric and Wendy Schmidt at the Institute for Advanced Studies, Princeton.
C. Cheng is supported by the William R. Hewlett Stanford graduate fellowship.
Acknowledgments
Part of this work was carried out while A. Montanari was on partial leave from Stanford and a Chief Scientist at Ndata Inc dba Project N. The present research is unrelated to A. Montanari’s activity while on leave.
Citation
Chen Cheng. Andrea Montanari. "Dimension free ridge regression." Ann. Statist. 52 (6) 2879 - 2912, December 2024. https://doi.org/10.1214/24-AOS2449
Information