PAC-Bayesian High Dimensional Bipartite Ranking
Machine Learning
2019-05-20 v2 Statistics Theory
Statistics Theory
Abstract
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.
Cite
@article{arxiv.1511.02729,
title = {PAC-Bayesian High Dimensional Bipartite Ranking},
author = {Benjamin Guedj and Sylvain Robbiano},
journal= {arXiv preprint arXiv:1511.02729},
year = {2019}
}