Convergence and Mixing in Markov Chain Monte Carlo: Advanced Algorithms and Latest Developments

Stefano Peluso; Antonietta Mira

doi:10.1002/9780470061572

Convergence and Mixing in Markov Chain Monte Carlo: Advanced Algorithms and Latest Developments

Stefano Peluso, Antonietta Mira

Università Cattolica del Sacro Cuore

Risultato della ricerca: Contributo in libro › Voce in dizionario / enciclopedia

Abstract

We survey possible strategies to improve the performance of Markov chain Monte Carlo methods either by reducing the asymptotic variance of the resulting estimators or by increasing the speed of convergence to stationarity. Recent advances in the direction of the pseudomarginal approach, Gradient-based algorithms and Approximate Bayesian Computation are also highlighted.

Lingua originale	English
Titolo della pubblicazione ospite	Encyclopedia of Statistics in Quality and Reliability
Pagine	N/A
DOI	https://doi.org/10.1002/9780470061572
Stato di pubblicazione	Pubblicato - 2015

Keywords

Adaptive MCMC
Approximate Bayesian Computation
Auxiliary variables
Delayed rejection
Langevin diffusions
Particle MCMC
Particle filters
Population Monte Carlo
Pseudomarginal approach
Simulated tempering
Slice sampler
hybrid Monte Carlo

Accesso al documento

10.1002/9780470061572

Altri file e collegamenti

Link a IRIS PubliCatt

Cita questo

@inbook{cffba9b17fbc4ec1b3532043af03c943,

title = "Convergence and Mixing in Markov Chain Monte Carlo: Advanced Algorithms and Latest Developments",

abstract = "We survey possible strategies to improve the performance of Markov chain Monte Carlo methods either by reducing the asymptotic variance of the resulting estimators or by increasing the speed of convergence to stationarity. Recent advances in the direction of the pseudomarginal approach, Gradient-based algorithms and Approximate Bayesian Computation are also highlighted.",

keywords = "Adaptive MCMC, Approximate Bayesian Computation, Auxiliary variables, Delayed rejection, Langevin diffusions, Particle MCMC, Particle filters, Population Monte Carlo, Pseudomarginal approach, Simulated tempering, Slice sampler, hybrid Monte Carlo, Adaptive MCMC, Approximate Bayesian Computation, Auxiliary variables, Delayed rejection, Langevin diffusions, Particle MCMC, Particle filters, Population Monte Carlo, Pseudomarginal approach, Simulated tempering, Slice sampler, hybrid Monte Carlo",

author = "Stefano Peluso and Antonietta Mira",

year = "2015",

doi = "10.1002/9780470061572",

language = "English",

isbn = "9780470018613",

pages = "N/A",

booktitle = "Encyclopedia of Statistics in Quality and Reliability",

}

TY - CHAP

T1 - Convergence and Mixing in Markov Chain Monte Carlo: Advanced Algorithms and Latest Developments

AU - Peluso, Stefano

AU - Mira, Antonietta

PY - 2015

Y1 - 2015

N2 - We survey possible strategies to improve the performance of Markov chain Monte Carlo methods either by reducing the asymptotic variance of the resulting estimators or by increasing the speed of convergence to stationarity. Recent advances in the direction of the pseudomarginal approach, Gradient-based algorithms and Approximate Bayesian Computation are also highlighted.

AB - We survey possible strategies to improve the performance of Markov chain Monte Carlo methods either by reducing the asymptotic variance of the resulting estimators or by increasing the speed of convergence to stationarity. Recent advances in the direction of the pseudomarginal approach, Gradient-based algorithms and Approximate Bayesian Computation are also highlighted.

KW - Adaptive MCMC

KW - Approximate Bayesian Computation

KW - Auxiliary variables

KW - Delayed rejection

KW - Langevin diffusions

KW - Particle MCMC

KW - Particle filters

KW - Population Monte Carlo

KW - Pseudomarginal approach

KW - Simulated tempering

KW - Slice sampler

KW - hybrid Monte Carlo

KW - Adaptive MCMC

KW - Approximate Bayesian Computation

KW - Auxiliary variables

KW - Delayed rejection

KW - Langevin diffusions

KW - Particle MCMC

KW - Particle filters

KW - Population Monte Carlo

KW - Pseudomarginal approach

KW - Simulated tempering

KW - Slice sampler

KW - hybrid Monte Carlo

UR - http://hdl.handle.net/10807/66037

U2 - 10.1002/9780470061572

DO - 10.1002/9780470061572

M3 - Entry for encyclopedia/dictionary

SN - 9780470018613

SP - N/A

BT - Encyclopedia of Statistics in Quality and Reliability

ER -

Convergence and Mixing in Markov Chain Monte Carlo: Advanced Algorithms and Latest Developments

Abstract

Keywords

Accesso al documento

Altri file e collegamenti

Fingerprint

Cita questo