A general purpose sampling algorithm for continuous distributions (the t-walk)
J. Andrés Christen,Colin Fox +1 more
Reads0
Chats0
TLDR
The t-walk as discussed by the authors is a general-purpose MCMC sampler for arbitrary continuous distributions that requires no tuning and is provably convergent under the usual mild requirements, but it is not suitable for high-dimensional problems.Abstract:
We develop a new general purpose MCMC sampler for arbitrary continuous distributions that requires no tuning. We call this MCMC the t-walk. The t-walk maintains two independent points in the sample space, and all moves are based on proposals that are then accepted with a standard Metropolis-Hastings acceptance probability on the product space. Hence the t-walk is provably convergent under the usual mild requirements. We restrict proposal distributions, or `moves', to those that produce an algorithm that is invariant to scale, and approximately invariant to affine transformations of the state space. Hence scaling of proposals, and effectively also coordinate transformations, that might be used to increase efficiency of the sampler, are not needed since the t-walk's operation is identical on any scaled version of the target distribution. Four moves are given that result in an effective sampling algorithm. We use the simple device of updating only a random subset of coordinates at each step to allow application of the t-walk to high-dimensional problems. In a series of test problems across dimensions we find that the t-walk is only a small factor less efficient than optimally tuned algorithms, but significantly outperforms general random-walk M-H samplers that are not tuned for specific problems. Further, the t-walk remains effective for target distributions for which no optimal affine transformation exists such as those where correlation structure is very different in differing regions of state space. Several examples are presented showing good mixing and convergence characteristics, varying in dimensions from 1 to 200 and with radically different scale and correlation structure, using exactly the same sampler. The t-walk is available for R, Python, MatLab and C++ at http://www.cimat.mx/~jac/twalk/read more
Citations
More filters
Journal ArticleDOI
Flexible paleoclimate age-depth models using an autoregressive gamma process
TL;DR: Christen et al. as discussed by the authors used a gamma-to-regressive semiparametric model with an arbitrary number of subdivisions along the sediment to estimate the age of sediment cores.
Journal ArticleDOI
A Stochastic Newton MCMC Method for Large-Scale Statistical Inverse Problems with Application to Seismic Inversion
TL;DR: This work addresses the solution of large-scale statistical inverse problems in the framework of Bayesian inference with a so-called Stochastic Monte Carlo method.
Journal ArticleDOI
The time-transgressive termination of the African Humid Period
Timothy M. Shanahan,Nicholas P. McKay,Konrad A Hughen,Jonathan T. Overpeck,Bette L. Otto-Bliesner,Clifford W. Heil,John W. King,Christopher A. Scholz,John A. Peck +8 more
TL;DR: In this article, the termination of humidity was spatially variable, moving towards progressively lower latitudes in Africa during the early to mid-Holocene, during which Africa was more humid than today.
Journal ArticleDOI
Parameter and State Model Reduction for Large-Scale Statistical Inverse Problems
TL;DR: A greedy algorithm for the construction of a reduced model with reduction in both parameter and state is developed for an efficient solution of statistical inverse problems governed by partial differential equations with distributed parameters.
Journal ArticleDOI
A general science-based framework for dynamical spatio-temporal models
TL;DR: In this article, the authors present a framework for incorporating scientific information to motivate dynamical spatio-temporal models and demonstrate that it accommodates many different classes of scientific-based parameterizations as special cases.
References
More filters
Book
Monte Carlo Statistical Methods (Springer Texts in Statistics)
TL;DR: It is possible to locate as well as download monte carlo statistical methods springer texts in statistics Book.
Journal ArticleDOI
A tutorial on adaptive MCMC
TL;DR: This work proposes a series of novel adaptive algorithms which prove to be robust and reliable in practice and reviews criteria and the useful framework of stochastic approximation, which allows one to systematically optimise generally used criteria.