Titre :

PAC-Bayesian High Dimensional Bipartite Ranking

Auteur(s) :

Guedj, Benjamin [Auteur]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Robbiano, Sylvain [Auteur]

Titre de la revue :

Journal of Statistical Planning and Inference

Éditeur :

Elsevier

Date de publication :

2018

ISSN :

0378-3758

Mot(s)-clé(s) :

Supervised Statistical Learning
Bipartite Ranking
High Dimension and Sparsity
MCMC
PAC-Bayesian Aggregation

Discipline(s) HAL :

Statistiques [stat]/Machine Learning [stat.ML]

Résumé en anglais : [en]

This paper is devoted to the bipartite ranking problem, a classical statistical learning task, in a high dimensional setting. We propose a scoring and ranking strategy based on the PAC-Bayesian approach. We consider nonlinear ...
Lire la suite >This paper is devoted to the bipartite ranking problem, a classical statistical learning task, in a high dimensional setting. We propose a scoring and ranking strategy based on the PAC-Bayesian approach. We consider nonlinear additive scoring functions, and we derive non-asymptotic risk bounds under a sparsity assumption. In particular, oracle inequalities in probability holding under a margin condition assess the performance of our procedure, and prove its minimax optimality. An MCMC-flavored algorithm is proposed to implement our method, along with its behavior on synthetic and real-life datasets.Lire moins >

Langue :

Anglais

Audience :

Internationale

Vulgarisation :

Non

Établissement(s) :

CNRS
Université de Lille

Collections :

• METRICS : Evaluation des technologies de santé et des pratiques médicales - ULR 2694

Date de dépôt :

2020-06-08T14:11:43Z
2020-06-09T09:29:08Z