Section: New Results

Axis 2: PAC-Bayesian high dimensional bipartite ranking

Participant : Benjamin Guedj.

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.

Joint work with Sylvain Robbiano. Paper published in Journal of Statistical Planning and Inference: [16].