English

Bayesian Bootstraps for Massive Data

Computation 2019-03-25 v2

Abstract

In this article, we present data-subsetting algorithms that allow for the approximate and scalable implementation of the Bayesian bootstrap. They are analogous to two existing algorithms in the frequentist literature: the bag of little bootstraps (Kleiner et al., 2014) and the subsampled double bootstrap (SDB; Sengupta et al., 2016). Our algorithms have appealing theoretical and computational properties that are comparable to those of their frequentist counterparts. Additionally, we provide a strategy for performing lossless inference for a class of functionals of the Bayesian bootstrap, and briefly introduce extensions to the Dirichlet Process.

Keywords

Cite

@article{arxiv.1705.09998,
  title  = {Bayesian Bootstraps for Massive Data},
  author = {Andrés F. Barrientos and Víctor Peña},
  journal= {arXiv preprint arXiv:1705.09998},
  year   = {2019}
}