Piecewise deterministic Markov processes for scalable Monte Carlo on restricted domains

Journal article (2018)

Authors

G.N.J.C. Bierkens Statistics - EEMCS
Alexandre Bouchard-Côté University of British Columbia
Arnaud Doucet University of Oxford
Andrew B. Duncan University of Sussex
Paul Fearnhead University of Lancaster
Thibaut Lienart University of Oxford
Gareth Roberts University of Warwick
Sebastian J. Vollmer University of Warwick
Research Group
Statistics (EEMCS) (TU Delft)
Copyright: © 2018 G.N.J.C. Bierkens, Alexandre Bouchard-Côté, Arnaud Doucet, Andrew B. Duncan, Paul Fearnhead, Thibaut Lienart, Gareth Roberts, Sebastian J. Vollmer
DOI: https://doi.org/10.1016/j.spl.2018.02.021
More Info
expand_more

Published Date

2018

Language

English

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Delft Institute of Applied Mathematics

Research Group

Statistics

Abstract

Piecewise Deterministic Monte Carlo algorithms enable simulation from a posterior distribution, whilst only needing to access a sub-sample of data at each iteration. We show how they can be implemented in settings where the parameters live on a restricted domain.

Files

Manuscript.pdf
(.pdf | 0.664 Mb)
- Embargo expired in 25-05-2020
help_outline