Concentration inequalities for the exponential weighting method

Abstract : The paper is concerned with recovering an unknown vector from noisy data with the help of a family of ordered smoothers [11]. The estimators withing this family are aggregated based on the exponential weighting method and the performance of the aggregated estimate is measured by the excess risk controlling deviation of the square losses from the oracle risk. Based on natural statistical properties of ordered smoothers, we propose a novel method for obtaining concentration inequalities for the exponential weighting method.
Document type :
Journal articles
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01292413
Contributor : Yuri Goloubev <>
Submitted on : Wednesday, March 23, 2016 - 9:40:17 AM
Last modification on : Monday, March 4, 2019 - 2:04:19 PM
Long-term archiving on : Monday, November 14, 2016 - 1:54:46 AM

Files

excess-risk-bounds.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Yu Golubev, D Ostrovski. Concentration inequalities for the exponential weighting method. Mathematical Methods of Statistics, Allerton Press, Springer (link), 2014, ⟨10.3103/S1066530714010025⟩. ⟨hal-01292413⟩

Share

Metrics

Record views

169

Files downloads

206