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. 1809.10462
31
60

Robust covariance estimation under L4−L2L_4-L_2L4​−L2​ norm equivalence

27 September 2018
S. Mendelson
Nikita Zhivotovskiy
ArXivPDFHTML
Abstract

Let XXX be a centered random vector taking values in Rd\mathbb{R}^dRd and let Σ=E(X⊗X)\Sigma= \mathbb{E}(X\otimes X)Σ=E(X⊗X) be its covariance matrix. We show that if XXX satisfies an L4−L2L_4-L_2L4​−L2​ norm equivalence, there is a covariance estimator Σ^\hat{\Sigma}Σ^ that exhibits the optimal performance one would expect had XXX been a gaussian vector. The procedure also improves the current state-of-the-art regarding high probability bounds in the subgaussian case (sharp results were only known in expectation or with constant probability). In both scenarios the new bound does not depend explicitly on the dimension ddd, but rather on the effective rank of the covariance matrix Σ\SigmaΣ.

View on arXiv
Comments on this paper