Title :

PAC-Bayesian High Dimensional Bipartite Ranking

Author(s) :

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

Journal title :

Journal of Statistical Planning and Inference

Publisher :

Elsevier

Publication date :

2018

ISSN :

0378-3758

Keyword(s) :

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

HAL domain(s) :

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

English abstract : [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 ...
Show more >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.Show less >

Language :

Anglais

Audience :

Internationale

Popular science :

Non

Administrative institution(s) :

CNRS
Université de Lille

Collections :

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

Submission date :

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