SmallNoise Analysis and Symmetrization of Implicit Monte Carlo Samplers
Implicit samplers are algorithms for producing independent, weighted samples from multivariate probability distributions. These are often applied in Bayesian data assimilation algorithms. We use Laplace asymptotic expansions to analyze two implicit samplers in the small noise regime. Our analysis suggests a symmetrization of the algorithms that leads to improved implicit sampling schemes at a relatively small additional cost. Here, computational experiments confirm the theory and show that symmetrization is effective for small noise sampling problems.
 Authors:

^{[1]};
^{[2]};
^{[3]}
 Courant Institute, New York, NY (United States)
 Univ. of Arizona, Tucson, AZ (United States)
 Univ. of California, Berkeley, CA (United States); Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
 Publication Date:
 Grant/Contract Number:
 AC0205CH11231; DMS1217065; DMS1418775; DMS1419044
 Type:
 Accepted Manuscript
 Journal Name:
 Communications on Pure and Applied Mathematics
 Additional Journal Information:
 Journal Volume: 69; Journal Issue: 10; Journal ID: ISSN 00103640
 Publisher:
 Wiley
 Research Org:
 Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
 Sponsoring Org:
 USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC21); National Science Foundation (NSF)
 Country of Publication:
 United States
 Language:
 English
 Subject:
 97 MATHEMATICS AND COMPUTING
 OSTI Identifier:
 1418471
Goodman, Jonathan, Lin, Kevin K., and Morzfeld, Matthias. SmallNoise Analysis and Symmetrization of Implicit Monte Carlo Samplers. United States: N. p.,
Web. doi:10.1002/cpa.21592.
Goodman, Jonathan, Lin, Kevin K., & Morzfeld, Matthias. SmallNoise Analysis and Symmetrization of Implicit Monte Carlo Samplers. United States. doi:10.1002/cpa.21592.
Goodman, Jonathan, Lin, Kevin K., and Morzfeld, Matthias. 2015.
"SmallNoise Analysis and Symmetrization of Implicit Monte Carlo Samplers". United States.
doi:10.1002/cpa.21592. https://www.osti.gov/servlets/purl/1418471.
@article{osti_1418471,
title = {SmallNoise Analysis and Symmetrization of Implicit Monte Carlo Samplers},
author = {Goodman, Jonathan and Lin, Kevin K. and Morzfeld, Matthias},
abstractNote = {Implicit samplers are algorithms for producing independent, weighted samples from multivariate probability distributions. These are often applied in Bayesian data assimilation algorithms. We use Laplace asymptotic expansions to analyze two implicit samplers in the small noise regime. Our analysis suggests a symmetrization of the algorithms that leads to improved implicit sampling schemes at a relatively small additional cost. Here, computational experiments confirm the theory and show that symmetrization is effective for small noise sampling problems.},
doi = {10.1002/cpa.21592},
journal = {Communications on Pure and Applied Mathematics},
number = 10,
volume = 69,
place = {United States},
year = {2015},
month = {7}
}