PAC-Bayesian aggregation of affine estimators

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

Cited literature [59 references]  Display  Hide  Download

https://hal.inria.fr/hal-01070805
Contributor : Erwan Le Pennec <>
Submitted on : Tuesday, January 30, 2018 - 8:43:33 PM
Last modification on : Wednesday, December 4, 2019 - 1:34:07 PM
Long-term archiving on: Friday, May 25, 2018 - 5:17:45 PM

Files

ArticlePAC_HAL.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01070805, version 3
  • ARXIV : 1410.0661

Citation

Lucie Montuelle, Erwan Le Pennec. PAC-Bayesian aggregation of affine estimators. 2018. ⟨hal-01070805v3⟩

Share

Metrics

Record views

384

Files downloads

449