sns: Stochastic Newton Sampler (SNS)

Stochastic Newton Sampler (SNS) is a Metropolis-Hastings-based, Markov Chain Monte Carlo sampler for twice differentiable, log-concave probability density functions (PDFs) where the proposal density function is a multivariate Gaussian resulting from a second-order Taylor-series expansion of log-density around the current point. The mean of the Gaussian proposal is the full Newton-Raphson step from the current point. A Boolean flag allows for switching from SNS to Newton-Raphson optimization (by choosing the mean of proposal function as next point). This can be used during burn-in to get close to the mode of the PDF (which is unique due to concavity). For high-dimensional densities, mixing can be improved via 'state space partitioning' strategy, in which SNS is applied to disjoint subsets of state space, wrapped in a Gibbs cycle. Numerical differentiation is available when analytical expressions for gradient and Hessian are not available. Facilities for validation and numerical differentiation of log-density are provided.

AuthorAlireza S. Mahani, Asad Hasan, Marshall Jiang, Mansour T.A. Sharabiani
Date of publication2016-10-25 10:31:12
MaintainerAlireza Mahani <alireza.s.mahani@gmail.com>
LicenseGPL (>= 2)
Version1.1.2

View on CRAN

Files

sns
sns/inst
sns/inst/CITATION
sns/inst/doc
sns/inst/doc/SNS.Rnw
sns/inst/doc/SNS.R
sns/inst/doc/SNS.pdf
sns/NAMESPACE
sns/R
sns/R/sns.R sns/R/sns.methods.R sns/R/ess.R sns/R/zzz.R
sns/vignettes
sns/vignettes/SNS.bib
sns/vignettes/fig_bench_corr_binomial.pdf
sns/vignettes/fig_bench_N_binomial.pdf
sns/vignettes/fig_bench_N_exponential.pdf
sns/vignettes/fig_bench_corr_exponential.pdf
sns/vignettes/SNS.Rnw
sns/vignettes/fig_bench_N_poisson.pdf
sns/vignettes/fig_bench_corr_poisson.pdf
sns/MD5
sns/build
sns/build/vignette.rds
sns/DESCRIPTION
sns/ChangeLog
sns/man
sns/man/plot.sns.Rd sns/man/sns.fghEval.numaug.Rd sns/man/summary.sns.Rd sns/man/predict.sns.Rd sns/man/sns.part.Rd sns/man/sns.check.logdensity.Rd sns/man/sns.run.Rd sns/man/ess.Rd sns/man/sns.Rd

Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.