AISTATS 2022poster41 citations

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

Guillaume Wang, Konstantin Donhauser, Fanny Yang

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.

BibTeX
@InProceedings{pmlr-v151-wang22k,
  title = 	 { Tight bounds for minimum $\ell_1$-norm interpolation of noisy data },
  author =       {Wang, Guillaume and Donhauser, Konstantin and Yang, Fanny},
  booktitle = 	 {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {10572--10602},
  year = 	 {2022},
  editor = 	 {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel},
  volume = 	 {151},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {28--30 Mar},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v151/wang22k/wang22k.pdf},
  url = 	 {https://proceedings.mlr.press/v151/wang22k.html},
  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. }
}
Tight bounds for minimum $\ell_1$-norm interpolation of noisy data · AISTATS 2022