Geodesic
Estimator selection
M. Lerasle1
1 Univ. Nice Sophia Antipolis LJAD CNRS UMR 7351 06100 Nice France
ESAIM. Proceedings, Tome 51 (2015), pp. 232-245 Cet article a éte moissonné depuis la source EDP Sciences

Voir la notice de l'article

The paper presents recent developments of the theory of estimator selection. We introduce, in the density estimation framework, the main methods used by the participants of the session ”Variable and estimator selection” in the Journées MAS 2014. The purpose of the selection is always to prove oracle inequalities, that is, to compare the selected estimator with the best estimator in the original collection via some risk function. The first part of the paper deals with the selection by minimization of a penalized empirical loss and the second presents the methods based on robust tests.
DOI : 10.1051/proc/201551013

M. Lerasle 1

1 Univ. Nice Sophia Antipolis LJAD CNRS UMR 7351 06100 Nice France 
@article{EP_2015_51_a13,
     author = {M. Lerasle},
     title = {Estimator selection},
     journal = {ESAIM. Proceedings},
     pages = {232--245},
     year = {2015},
     volume = {51},
     doi = {10.1051/proc/201551013},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.1051/proc/201551013/}
}
TY  - JOUR
AU  - M. Lerasle
TI  - Estimator selection
JO  - ESAIM. Proceedings
PY  - 2015
SP  - 232
EP  - 245
VL  - 51
UR  - http://geodesic.mathdoc.fr/articles/10.1051/proc/201551013/
DO  - 10.1051/proc/201551013
LA  - en
ID  - EP_2015_51_a13
ER  - 
%0 Journal Article
%A M. Lerasle
%T Estimator selection
%J ESAIM. Proceedings
%D 2015
%P 232-245
%V 51
%U http://geodesic.mathdoc.fr/articles/10.1051/proc/201551013/
%R 10.1051/proc/201551013
%G en
%F EP_2015_51_a13
M. Lerasle. Estimator selection. ESAIM. Proceedings, Tome 51 (2015), pp. 232-245. doi: 10.1051/proc/201551013

Cité par Sources :