Authors: | Alireza S. Mahani, Asad Hasan, Marshall Jiang, Mansour T. A. Sharabiani | ||||
Title: | Stochastic Newton Sampler: The R Package sns | ||||
Abstract: | The R package sns implements the stochastic Newton sampler (SNS), a MetropolisHastings Markov chain Monte Carlo (MCMC) algorithm where the proposal density function is a multivariate Gaussian based on a local, second-order Taylor-series expansion of log-density. The mean of the proposal function is the full Newton step in the NewtonRaphson optimization algorithm. Taking advantage of the local, multivariate geometry captured in log-density Hessian allows SNS to be more efficient than univariate samplers, approaching independent sampling as the density function increasingly resembles a multivariate Gaussian. SNS requires the log-density Hessian to be negative-definite everywhere in order to construct a valid proposal function. This property holds, or can be easily checked, for many GLM-like models. When the initial point is far from density peak, running SNS in non-stochastic mode by taking the Newton step - augmented with line search - allows the MCMC chain to converge to high-density areas faster. For high-dimensional problems, partitioning the state space into lower-dimensional subsets, and applying SNS to the subsets within a Gibbs sampling framework can significantly improve the mixing of SNS chains. In addition to the above strategies for improving convergence and mixing, sns offers utilities for diagnostics and visualization, sample-based calculation of Bayesian predictive posterior distributions, numerical differentiation, and log-density validation. | ||||
Page views:: 1458. Submitted: 2015-02-18. Published: 2016-10-27. |
|||||
Paper: |
Stochastic Newton Sampler: The R Package sns
Download PDF
(Downloads: 758)
|
||||
Supplements: |
| ||||
DOI: |
10.18637/jss.v074.c02
|
![]() This work is licensed under the licenses Paper: Creative Commons Attribution 3.0 Unported License Code: GNU General Public License (at least one of version 2 or version 3) or a GPL-compatible license. |