PAC-Bayesian aggregation of affine estimatorsReport as inadecuate

PAC-Bayesian aggregation of affine estimators - Download this document for free, or read online. Document in PDF available to download.

1 LPMA - Laboratoire de Probabilités et Modèles Aléatoires 2 CMAP - Centre de Mathématiques Appliquées - Ecole Polytechnique 3 XPOP - Modélisation en pharmacologie de population Inria Saclay - Ile de France

Abstract : Aggregating estimators using exponential weights depending on their risk performs well in expectation, but sadly not in probability. Considering exponential weights of a penalized risk is a way to overcome this issue. We focus on the fixed design regression framework with sub-Gaussian noise and provide penalties allowing to obtain oracle inequalities in deviation for the aggregation of affine estimators. Sharp oracle inequalities are provided by a condition using the regression function-s norm. MSC 2010 subject classifications: Primary 62G08; secondary 62J02.

Keywords : Exponentially weighted aggregation Regression Oracle inequality Deviation

Author: Lucie Montuelle - Erwan Le Pennec -



Related documents