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. 2104.04416
20
7

Concentration study of M-estimators using the influence function

9 April 2021
Timothée Mathieu
ArXivPDFHTML
Abstract

We present a new finite-sample analysis of M-estimators of locations in Rd\mathbb{R}^dRd using the tool of the influence function. In particular, we show that the deviations of an M-estimator can be controlled thanks to its influence function (or its score function) and then, we use concentration inequality on M-estimators to investigate the robust estimation of the mean in high dimension in a corrupted setting (adversarial corruption setting) for bounded and unbounded score functions. For a sample of size nnn and covariance matrix Σ\SigmaΣ, we attain the minimax speed Tr(Σ)/n+∥Σ∥oplog⁡(1/δ)/n\sqrt{Tr(\Sigma)/n}+\sqrt{\|\Sigma\|_{op}\log(1/\delta)/n}Tr(Σ)/n​+∥Σ∥op​log(1/δ)/n​ with probability larger than 1−δ1-\delta1−δ in a heavy-tailed setting. One of the major advantages of our approach compared to others recently proposed is that our estimator is tractable and fast to compute even in very high dimension with a complexity of O(ndlog⁡(Tr(Σ)))O(nd\log(Tr(\Sigma)))O(ndlog(Tr(Σ))) where nnn is the sample size and Σ\SigmaΣ is the covariance matrix of the inliers. In practice, the code that we make available for this article proves to be very fast.

View on arXiv
Comments on this paper