hal-00664125, version 3
Statistical learning with indirect observations
(29/06/2012)
- 1 :
-
http://math.univ-angers.fr/
CNRS : UMR6093 – Université d'Angers 2 Boulevard Lavoisier 49045 Angers cedex 01 France
Références bibliographiques
- Type de publication : Documents sans référence de publication (Preprint)
- Domaine :
Mathématiques/Statistiques Statistiques/Théorie Statistiques/Machine Learning - Titre : Statistical learning with indirect observations
- Résumé : Let $(X,Y)\in\mathcal{X}\times \mathcal{Y}$ be a random couple with unknown distribution $P$. Let $\GG$ be a class of measurable functions and $\ell$ a loss function. The problem of statistical learning deals with the estimation of the Bayes: $$g^*=\arg\min_{g\in\GG}\E_P \ell(g(X),Y). $$ In this paper, we study this problem when we deal with a contaminated sample $(Z_1,Y_1),\ldots , (Z_n,Y_n)$ of i.i.d. indirect observations. Each input $Z_i$, $i=1,\ldots ,n$ is distributed from a density $Af$, where $A$ is a known compact linear operator and $f$ is the density of the direct input $X$. \\ We derive fast rates of convergence for empirical risk minimizers based on regularization methods, such as deconvolution kernel density estimators or spectral cut-off. These results are comparable to the existing fast rates in \cite{kolt} for the direct case. It gives some insights into the effect of indirect measurements in the presence of fast rates of convergence.
- Langue du texte
intégral : Anglais - Date de production,
écriture : 29/06/2012 - Mots Clés : Statistical learning – Inverse problem – Classification – Deconvolution – Empirical processes – Fast rates
Liste des fichiers attachés à ce document :
![]() |
![]() |
noisystatlearn.pdf |
![]() |
PS |
![]() |
noisystatlearn.ps |
![]() |
TEX |
![]() |
noisystatlearn.tex |
![]() |
referencenoisy.bib |
![]() |
noisylearning.eps |
![]() |
imsart-ps.cnf |
![]() |
imsart.sty |
![]() |
imsart.cnf |
![]() |
imsart.cls |
- hal-00664125, version 3
- http://hal.archives-ouvertes.fr/hal-00664125
- oai:hal.archives-ouvertes.fr:hal-00664125
- Contributeur :
- Soumis le : Mardi 10 Juillet 2012, 10:14:13
- Dernière modification le : Mardi 10 Juillet 2012, 10:18:22









Documents associés
Exporter