Early stopping for statistical inverse problems via truncated SVD estimation - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Electronic Journal of Statistics Année : 2018

Early stopping for statistical inverse problems via truncated SVD estimation

Résumé

We consider truncated SVD (or spectral cutoff , projection) es-timators for a prototypical statistical inverse problem in dimension D. Since calculating the singular value decomposition (SVD) only for the largest singular values is much less costly than the full SVD, our aim is to select a data-driven truncation level m ∈ {1,. .. , D} only based on the knowledge of the first m singular values and vectors. We analyse in detail whether sequential early stopping rules of this type can preserve statistical optimality. Information-constrained lower bounds and matching upper bounds for a residual based stopping rule are provided, which give a clear picture in which situation optimal sequential adaptation is feasible. Finally, a hybrid two-step approach is proposed which allows for classical oracle inequalities while considerably reducing numerical complexity. MSC 2010 subject classifications: 65J20, 62G07.
Fichier principal
Vignette du fichier
euclid.ejs.1538121641.pdf (436.59 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01966326 , version 1 (28-12-2018)

Identifiants

Citer

Gilles Blanchard, Marc Hoffmann, Markus Reiss. Early stopping for statistical inverse problems via truncated SVD estimation. Electronic Journal of Statistics , 2018, 12 (2), pp.3204-3231. ⟨10.1214/18-ejs1482⟩. ⟨hal-01966326⟩
97 Consultations
56 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More