Concentration study of M-estimators using the influence function - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Electronic Journal of Statistics Année : 2022

Concentration study of M-estimators using the influence function

Résumé

We present a new finite-sample analysis of M-estimators of locations in a Hilbert space 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 n and covariance matrix Σ, we attain the minimax speed T r(Σ)/n + Σ op log(1/δ)/n with probability larger than 1 − 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(nd log(T r(Σ))) where n is the sample size and Σ is the covariance matrix of the inliers and in the code that we make available for this article is tested to be very fast.
Fichier principal
Vignette du fichier
22-EJS2030.pdf (588.11 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03757720 , version 1 (22-08-2022)

Identifiants

Citer

Timothée Mathieu. Concentration study of M-estimators using the influence function. Electronic Journal of Statistics , 2022, 16 (1), pp.3695-3750. ⟨10.1214/22-ejs2030⟩. ⟨hal-03757720⟩
45 Consultations
52 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More