Piecewise deterministic Markov processes for scalable Monte Carlo on restricted domains

Joris Bierkens; Alexandre Bouchard-Côté; Arnaud  Doucet; Andrew B.  Duncan; Paul  Fearnhead; Thibaut  Lienart; Gareth Roberts; Sebastian J.  Vollmer

doi:10.1016/j.spl.2018.02.021

Piecewise deterministic Markov processes for scalable Monte Carlo on restricted domains

Joris Bierkens^*, Alexandre Bouchard-Côté, Arnaud Doucet, Andrew B. Duncan, Paul Fearnhead, Thibaut Lienart, Gareth Roberts, Sebastian J. Vollmer

^*Corresponding author for this work

Statistics

Research output: Contribution to journal › Article › Scientific › peer-review

24 Citations (Scopus)

26 Downloads (Pure)

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.

Original language	English
Pages (from-to)	148-154
Number of pages	7
Journal	Statistics and Probability Letters
Volume	136
DOIs	https://doi.org/10.1016/j.spl.2018.02.021
Publication status	Published - 2018

Bibliographical note

Accepted author manuscript

Keywords

Bayesian statistics
Logistic regression
MCMC
Piecewise deterministic Markov processes

Access to Document

10.1016/j.spl.2018.02.021

manuscriptAccepted author manuscript, 558 KBLicence: CC BY-NC-ND

Cite this

@article{500507b7b9f241a9816d2f324ba9fb50,

title = "Piecewise deterministic Markov processes for scalable Monte Carlo on restricted domains",

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.",

keywords = "Bayesian statistics, Logistic regression, MCMC, Piecewise deterministic Markov processes",

author = "Joris Bierkens and Alexandre Bouchard-C{\^o}t{\'e} and Arnaud Doucet and Duncan, {Andrew B.} and Paul Fearnhead and Thibaut Lienart and Gareth Roberts and Vollmer, {Sebastian J.}",

note = "Accepted author manuscript",

year = "2018",

doi = "10.1016/j.spl.2018.02.021",

language = "English",

volume = "136",

pages = "148--154",

journal = "Statistics and Probability Letters",

issn = "0167-7152",

publisher = "Elsevier",

}

TY - JOUR

T1 - Piecewise deterministic Markov processes for scalable Monte Carlo on restricted domains

AU - Bierkens, Joris

AU - Bouchard-Côté, Alexandre

AU - Doucet, Arnaud

AU - Duncan, Andrew B.

AU - Fearnhead, Paul

AU - Lienart, Thibaut

AU - Roberts, Gareth

AU - Vollmer, Sebastian J.

N1 - Accepted author manuscript

PY - 2018

Y1 - 2018

N2 - 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.

AB - 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.

KW - Bayesian statistics

KW - Logistic regression

KW - MCMC

KW - Piecewise deterministic Markov processes

UR - http://www.scopus.com/inward/record.url?scp=85042870017&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2018.02.021

DO - 10.1016/j.spl.2018.02.021

M3 - Article

AN - SCOPUS:85042870017

SN - 0167-7152

VL - 136

SP - 148

EP - 154

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

ER -

Piecewise deterministic Markov processes for scalable Monte Carlo on restricted domains

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this