PAC-Bayesian aggregation of affine estimators
Statistics Theory
2018-02-01 v3 Statistics Theory
Abstract
Aggregating estimators using exponential weights depending on their risk appears optimal in expectation but not in probability. We use here a slight overpenalization to obtain oracle inequality in probability for such an explicit aggregation procedure. We focus on the fixed design regression framework and the aggregation of affine estimators and obtain results for a large family of affine estimators under a non necessarily independent sub-Gaussian noise assumptions.
Cite
@article{arxiv.1410.0661,
title = {PAC-Bayesian aggregation of affine estimators},
author = {Lucie Montuelle and Erwan Le Pennec},
journal= {arXiv preprint arXiv:1410.0661},
year = {2018}
}