Guaranteed characterization of exact non-asymptotic confidence regions - CentraleSupélec Access content directly
Preprints, Working Papers, ... Year :

Guaranteed characterization of exact non-asymptotic confidence regions

Abstract

In parameter estimation, it is often desirable to supplement the estimates with an assessment of their quality. A new family of methods proposed by Campi et al. for this purpose is particularly attractive, as it makes it possible to obtain exact, non-asymptotic con dence regions under mild assumptions on the noise distribution. A bottleneck of this approach, however, is the numerical characterization of these con dence regions. So far, it has been carried out by gridding, which provides no guarantee as to its results and is only applicable to low dimensional spaces. This paper shows how interval analysis can contribute to removing this bottleneck.
Fichier principal
Vignette du fichier
Automatica_Revised_v4.pdf (313.04 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00879937 , version 1 (05-11-2013)

Identifiers

  • HAL Id : hal-00879937 , version 1

Cite

Michel Kieffer, Eric Walter. Guaranteed characterization of exact non-asymptotic confidence regions. 2013. ⟨hal-00879937⟩
265 View
375 Download

Share

Gmail Facebook Twitter LinkedIn More