Tight bounds for minimum l1-norm interpolation of noisy data

Code

• github.com/DonhauserK/DonhauserK.github.io
  none★ 0

Abstract

We provide matching upper and lower bounds of order ^2/(d/n) for the prediction error of the minimum _1-norm interpolator, a.k.a. basis pursuit. Our result is tight up to negligible terms when d n, and is the first to imply asymptotic consistency of noisy minimum-norm interpolation for isotropic features and sparse ground truths. Our work complements the literature on "benign overfitting" for minimum _2-norm interpolation, where asymptotic consistency can be achieved only when the features are effectively low-dimensional.

Reproductions