Deconvolution of repeated measurements corrupted by unknown noise - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2024

Deconvolution of repeated measurements corrupted by unknown noise

Résumé

Recent advances have demonstrated the possibility of solving the deconvolution problem without prior knowledge of the noise distribution. In this paper, we study the repeated measurements model, where information is derived from multiple measurements of X perturbed independently by additive errors. Our contributions include establishing identifiability without any assumption on the noise except for coordinate independence. We propose an estimator of the density of the signal for which we provide rates of convergence, and prove that it reaches the minimax rate in the case where the support of the signal is compact. Additionally, we propose a model selection procedure for adaptive estimation. Numerical simulations demonstrate the effectiveness of our approach even with limited sample sizes.
Fichier principal
Vignette du fichier
main.pdf (891.72 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04685944 , version 1 (03-09-2024)

Identifiants

  • HAL Id : hal-04685944 , version 1

Citer

Jeremie Capitao-Miniconi, Élisabeth Gassiat, Luc Lehéricy. Deconvolution of repeated measurements corrupted by unknown noise. 2024. ⟨hal-04685944⟩
14 Consultations
6 Téléchargements

Partager

More