Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

PAC-Bayesian aggregation of affine estimators

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.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [55 references]  Display  Hide  Download

https://hal.inria.fr/hal-01070805
Contributor : Erwan Le Pennec <>
Submitted on : Monday, October 24, 2016 - 4:52:42 PM
Last modification on : Thursday, March 26, 2020 - 9:14:35 PM

File

ArticlePAC_Arxiv.pdf
Files produced by the author(s)

Identifiers

Collections

UPMC | PMA

Citation

Lucie Montuelle, Erwan Le Pennec. PAC-Bayesian aggregation of affine estimators. 2016. ⟨hal-01070805v2⟩

Share

Metrics

Record views

308

Files downloads

172