English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Empirical risk minimization as parameter choice rule for general linear regularization methods.

Li, H., & Werner, F. (2020). Empirical risk minimization as parameter choice rule for general linear regularization methods. Annales de l'Institut Henri Poincaré, Probabilités et Statistiques, 56(1), 405-427. doi:10.1214/19-AIHP966.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0005-AD7A-0 Version Permalink: http://hdl.handle.net/21.11116/0000-0005-AD8B-C
Genre: Journal Article

Files

show Files
hide Files
:
3194320.pdf (Preprint), 406KB
Name:
3194320.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Li, H., Author
Werner, F.1, Author              
Affiliations:
1Research Group of Statistical Inverse-Problems in Biophysics, MPI for Biophysical Chemistry, Max Planck Society, ou_1113580              

Content

show
hide
Free keywords: Statistical inverse problem; Regularization method; Filter-based inversion; A-posteriori parameter choice rule; Order optimality; Exponential bounds; Oracle inequality
 Abstract: We consider the statistical inverse problem to recover f from noisy measurements Y = Tf + sigma xi where xi is Gaussian white noise and T a compact operator between Hilbert spaces. Considering general reconstruction methods of the form (f) over cap (alpha) = q(alpha) (T*T)T*Y with an ordered filter q(alpha), we investigate the choice of the regularization parameter alpha by minimizing an unbiased estiate of the predictive risk E[parallel to T f - T (f) over cap (alpha)parallel to(2)]. The corresponding parameter alpha(pred) and its usage are well-known in the literature, but oracle inequalities and optimality results in this general setting are unknown. We prove a (generalized) oracle inequality, which relates the direct risk E[parallel to f - (f) over cap (alpha pred)parallel to(2)] with the oracle prediction risk inf(alpha>0) E[parallel to T f - T (f) over cap (alpha)parallel to(2)]. From this oracle inequality we are then able to conclude that the investigated parameter choice rule is of optimal order in the minimax sense. Finally we also present numerical simulations, which support the order optimality of the method and the quality of the parameter choice in finite sample situations.

Details

show
hide
Language(s): eng - English
 Dates: 2020
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1214/19-AIHP966
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Annales de l'Institut Henri Poincaré, Probabilités et Statistiques
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 56 (1) Sequence Number: - Start / End Page: 405 - 427 Identifier: arXiv: 1703.07809