English

Robust Bayes-Like Estimation: Rho-Bayes estimation

Statistics Theory 2020-03-30 v2 Statistics Theory

Abstract

We consider the problem of estimating the joint distribution PP of nn independent random variables within the Bayes paradigm from a non-asymptotic point of view. Assuming that PP admits some density ss with respect to a given reference measure, we consider a density model S\overline S for ss that we endow with a prior distribution π\pi (with support S\overline S) and we build a robust alternative to the classical Bayes posterior distribution which possesses similar concentration properties around ss whenever it belongs to the model S\overline S. Furthermore, in density estimation, the Hellinger distance between the classical and the robust posterior distributions tends to 0, as the number of observations tends to infinity, under suitable assumptions on the model and the prior, provided that the model S\overline S contains the true density ss. However, unlike what happens with the classical Bayes posterior distribution, we show that the concentration properties of this new posterior distribution are still preserved in the case of a misspecification of the model, that is when ss does not belong to S\overline S but is close enough to it with respect to the Hellinger distance.

Keywords

Cite

@article{arxiv.1711.08328,
  title  = {Robust Bayes-Like Estimation: Rho-Bayes estimation},
  author = {Yannick Baraud and Lucien Birgé},
  journal= {arXiv preprint arXiv:1711.08328},
  year   = {2020}
}

Comments

68 pages

R2 v1 2026-06-22T22:54:07.675Z