Skip to Main content Skip to Navigation
Conference papers

Agrégation PAC-bayésienne d'estimateurs par projection

Abstract : Aggregating estimators using exponential weights depending on their risk performs well in expectation, but sadly not in probability. A way to overcome this issue is considering exponential weights of a penalized risk. In this case, an oracle inequality can be obtained in probability, but is not sharp. Taking into account the estimated function's norm in the penalty offers a sharp inequality.
Document type :
Conference papers
Complete list of metadata

Cited literature [3 references]  Display  Hide  Download

https://hal.inria.fr/hal-01097173
Contributor : Lucie Montuelle <>
Submitted on : Saturday, January 24, 2015 - 2:20:07 PM
Last modification on : Wednesday, September 16, 2020 - 5:09:18 PM
Long-term archiving on: : Saturday, April 25, 2015 - 10:05:40 AM

Files

TexteLong_vmodif.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01097173, version 1

Collections

Citation

Lucie Montuelle, Erwan Le Pennec. Agrégation PAC-bayésienne d'estimateurs par projection. 46e Journées de Statistique, SFdS, Jun 2014, Rennes, France. ⟨hal-01097173⟩

Share

Metrics

Record views

246

Files downloads

110