 |
|
|
|
| HAL : hal-00722969, version 3 |
| DOI : 10.1214/13-EJS771 |
| Fiche détaillée |  Récupérer au format |
|
|
| Electronic Journal of Statistics 7 (2013) 264--291 |
|
|
| Versions disponibles : | v1 (07-08-2012) | v2 (21-12-2012) | v3 (04-02-2013) |
|
|
|
|
| PAC-Bayesian Estimation and Prediction in Sparse Additive Models |
|
|
Benjamin Guedj 1Pierre Alquier 2 |
|
|
| (25/01/2013) |
|
|
|
| The present paper is about estimation and prediction in high-dimensional additive models under a sparsity assumption ($p\gg n$ paradigm). A PAC-Bayesian strategy is investigated, delivering oracle inequalities in probability. The implementation is performed through recent outcomes in high-dimensional MCMC algorithms, and the performance of our method is assessed on simulated data. |
|
|
|
|
|
|
|
|
|
|
|
| 1 : | Laboratoire de Statistique Théorique et Appliquée (LSTA) |
|
|
|
Université Pierre et Marie Curie [UPMC] - Paris VI |
|
|
| 2 : | School of Mathematical Sciences |
|
|
|
University College Dublin |
|
|
|
|
|
|
|
|
|
| Domaine | : | Statistiques/Méthodologie Statistiques/Théorie |
|
|
| Additive models – sparsity – regression estimation – PAC-Bayesian bounds – oracle inequality – MCMC – stochastic search |
|
|
|
| Liste des fichiers attachés à ce document : | |||||
|
|||||
|
|
|
| hal-00722969, version 3 | |
| http://hal.archives-ouvertes.fr/hal-00722969 | |
| oai:hal.archives-ouvertes.fr:hal-00722969 | |
| Contributeur : Benjamin Guedj | |
| Soumis le : Vendredi 1 Février 2013, 11:56:05 | |
| Dernière modification le : Lundi 4 Février 2013, 10:29:32 | |
