Article Dans Une Revue Journal of Statistical Planning and Inference Année : 2018

PAC-Bayesian High Dimensional Bipartite Ranking

Résumé

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.

Fichier principal
Vignette du fichier
GuedjRobbiano2015.pdf (1.04 Mo) Télécharger le fichier
Loading...

Dates et versions

hal-01226472 , version 1 (10-11-2015)

Licence

Identifiants

Citer

Benjamin Guedj, Sylvain Robbiano. PAC-Bayesian High Dimensional Bipartite Ranking. Journal of Statistical Planning and Inference, 2018, ⟨10.1016/j.jspi.2017.10.010⟩. ⟨hal-01226472⟩
537 Consultations
308 Téléchargements

Altmetric

Partager

  • More