Tight bounds for minimum $\ell_1$-norm interpolation of noisy data

Guillaume Wang · Konstantin Donhauser · Fanny Yang

[ Abstract ]
Mon 28 Mar 4:30 a.m. PDT — 6 a.m. PDT

Abstract: We provide matching upper and lower bounds of order $\sigma^2/\log(d/n)$ for the prediction error of the minimum $\ell_1$-norm interpolator, a.k.a. basis pursuit. Our result is tight up to negligible terms when $d \gg n$, 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 $\ell_2$-norm interpolation, where asymptotic consistency can be achieved only when the features are effectively low-dimensional.

Chat is not available.