ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2208.05447
43
3

Robust Methods for High-Dimensional Linear Learning

10 August 2022
Ibrahim Merad
Stéphane Gaïffas
    OOD
ArXivPDFHTML
Abstract

We propose statistically robust and computationally efficient linear learning methods in the high-dimensional batch setting, where the number of features ddd may exceed the sample size nnn. We employ, in a generic learning setting, two algorithms depending on whether the considered loss function is gradient-Lipschitz or not. Then, we instantiate our framework on several applications including vanilla sparse, group-sparse and low-rank matrix recovery. This leads, for each application, to efficient and robust learning algorithms, that reach near-optimal estimation rates under heavy-tailed distributions and the presence of outliers. For vanilla sss-sparsity, we are able to reach the slog⁡(d)/ns\log (d)/nslog(d)/n rate under heavy-tails and η\etaη-corruption, at a computational cost comparable to that of non-robust analogs. We provide an efficient implementation of our algorithms in an open-source Python\mathtt{Python}Python library called linlearn\mathtt{linlearn}linlearn, by means of which we carry out numerical experiments which confirm our theoretical findings together with a comparison to other recent approaches proposed in the literature.

View on arXiv
Comments on this paper