Using parallel computation to improve Independent Metropolis-Hastings based estimation. Jacob, P., Robert, C. P, & Smith, M. H arXiv, stat.CO, 2010. abstract bibtex In this paper, we consider the implications of the fact that parallel raw-power can be exploited by a generic Metropolis-Hastings algorithm if the proposed values are independent. In particular, we present improvements to the independent Metropolis-Hastings algorithm that significantly decrease the variance of any estimator derived from the MCMC output, for a null computing cost since those improvements are based on a fixed number of target density evaluations. Furthermore, the techniques developed in this paper do not jeopardize the Markovian convergence properties of the algorithm, since they are based on the Rao-Blackwell principles of Gelfand and Smith (1990), already exploited in Casella and Robert (1996), Atchade and Perron (2005) and Douc and Robert (2010). We illustrate those improvement both on a toy normal example and on a classical probit regression model but insist on the fact that they are universally applicable.
@Article{Jacob2010,
author = {Jacob, Pierre and Robert, Christian P and Smith, Murray H},
title = {Using parallel computation to improve Independent Metropolis-Hastings based estimation},
journal = {arXiv},
volume = {stat.CO},
number = {},
pages = {},
year = {2010},
abstract = {In this paper, we consider the implications of the fact that parallel raw-power can be exploited by a generic Metropolis-Hastings algorithm if the proposed values are independent. In particular, we present improvements to the independent Metropolis-Hastings algorithm that significantly decrease the variance of any estimator derived from the MCMC output, for a null computing cost since those improvements are based on a fixed number of target density evaluations. Furthermore, the techniques developed in this paper do not jeopardize the Markovian convergence properties of the algorithm, since they are based on the Rao-Blackwell principles of Gelfand and Smith (1990), already exploited in Casella and Robert (1996), Atchade and Perron (2005) and Douc and Robert (2010). We illustrate those improvement both on a toy normal example and on a classical probit regression model but insist on the fact that they are universally applicable.},
location = {Universite Paris-Dauphine and CREST, France},
keywords = {cs.DC; cs.DS; stat.CO}}
Downloads: 0
{"_id":"7EDZJp3xHTQrN3shW","bibbaseid":"jacob-robert-smith-usingparallelcomputationtoimproveindependentmetropolishastingsbasedestimation-2010","authorIDs":[],"author_short":["Jacob, P.","Robert, C. P","Smith, M. H"],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Jacob"],"firstnames":["Pierre"],"suffixes":[]},{"propositions":[],"lastnames":["Robert"],"firstnames":["Christian","P"],"suffixes":[]},{"propositions":[],"lastnames":["Smith"],"firstnames":["Murray","H"],"suffixes":[]}],"title":"Using parallel computation to improve Independent Metropolis-Hastings based estimation","journal":"arXiv","volume":"stat.CO","number":"","pages":"","year":"2010","abstract":"In this paper, we consider the implications of the fact that parallel raw-power can be exploited by a generic Metropolis-Hastings algorithm if the proposed values are independent. In particular, we present improvements to the independent Metropolis-Hastings algorithm that significantly decrease the variance of any estimator derived from the MCMC output, for a null computing cost since those improvements are based on a fixed number of target density evaluations. Furthermore, the techniques developed in this paper do not jeopardize the Markovian convergence properties of the algorithm, since they are based on the Rao-Blackwell principles of Gelfand and Smith (1990), already exploited in Casella and Robert (1996), Atchade and Perron (2005) and Douc and Robert (2010). We illustrate those improvement both on a toy normal example and on a classical probit regression model but insist on the fact that they are universally applicable.","location":"Universite Paris-Dauphine and CREST, France","keywords":"cs.DC; cs.DS; stat.CO","bibtex":"@Article{Jacob2010,\nauthor = {Jacob, Pierre and Robert, Christian P and Smith, Murray H}, \ntitle = {Using parallel computation to improve Independent Metropolis-Hastings based estimation}, \njournal = {arXiv}, \nvolume = {stat.CO}, \nnumber = {}, \npages = {}, \nyear = {2010}, \nabstract = {In this paper, we consider the implications of the fact that parallel raw-power can be exploited by a generic Metropolis-Hastings algorithm if the proposed values are independent. In particular, we present improvements to the independent Metropolis-Hastings algorithm that significantly decrease the variance of any estimator derived from the MCMC output, for a null computing cost since those improvements are based on a fixed number of target density evaluations. Furthermore, the techniques developed in this paper do not jeopardize the Markovian convergence properties of the algorithm, since they are based on the Rao-Blackwell principles of Gelfand and Smith (1990), already exploited in Casella and Robert (1996), Atchade and Perron (2005) and Douc and Robert (2010). We illustrate those improvement both on a toy normal example and on a classical probit regression model but insist on the fact that they are universally applicable.}, \nlocation = {Universite Paris-Dauphine and CREST, France}, \nkeywords = {cs.DC; cs.DS; stat.CO}}\n\n\n","author_short":["Jacob, P.","Robert, C. P","Smith, M. H"],"key":"Jacob2010","id":"Jacob2010","bibbaseid":"jacob-robert-smith-usingparallelcomputationtoimproveindependentmetropolishastingsbasedestimation-2010","role":"author","urls":{},"keyword":["cs.DC; cs.DS; stat.CO"],"downloads":0},"bibtype":"article","biburl":"https://gist.githubusercontent.com/stuhlmueller/a37ef2ef4f378ebcb73d249fe0f8377a/raw/6f96f6f779501bd9482896af3e4db4de88c35079/references.bib","creationDate":"2020-01-27T02:13:34.411Z","downloads":0,"keywords":["cs.dc; cs.ds; stat.co"],"search_terms":["using","parallel","computation","improve","independent","metropolis","hastings","based","estimation","jacob","robert","smith"],"title":"Using parallel computation to improve Independent Metropolis-Hastings based estimation","year":2010,"dataSources":["hEoKh4ygEAWbAZ5iy"]}