One-shot CFTP; application to a class of truncated Gaussian densities

DOI10.1007/S11009-005-5001-2MaRDI QIDQ2433243zbMATH OpenOpenAlexFDO

Authors Alexandros Beskos, Gareth O. Roberts

Publication date 27 October 2006

Published in Methodology and Computing in Applied Probability (Search for Journal in Brave)

Full work available at URL https://discovery.ucl.ac.uk/id/eprint/10050410/

zbMATH Keywords

algorithmscomputation timenumerical experimentsone-shot couplingrandomnesstruncated Gaussian density

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Numerical analysis or methods applied to Markov chains (65C40)

Review text

The authors introduce a new method for the perfect simulation of multi-variate densities. The method can be applied in various settings. The algorithms presented use the Ro-CFTP protocol and rely on the construction of blocks of three different stages. The theoretical foundation is established by theorems and algorithms. Numerical experiments are as well performed for the validation and completeness of the theory proposed. It is an excellent research.

Recommendations

• Catalytic perfect simulation
• Perfectly random sampling of truncated multinormal distributions
• Perfect simulation
• Perfect Simulation of Conditionally Specified Models
• Perfect simulation with exponential tails on the running time

Cites work

• Bivariate Distributions With Exponential Conditionals
• Catalytic perfect simulation
• Conditional specification of statistical models.
• Exact Sampling from a Continuous State Space
• Exact sampling with coupled Markov chains and applications to statistical mechanics
• How to couple from the past using a read-once source of randomness
• scientific article; zbMATH DE number 3954145 (Why is no real title available?)
• scientific article; zbMATH DE number 3215568 (Why is no real title available?)
• scientific article; zbMATH DE number 3348831 (Why is no real title available?)
• Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
• One-shot coupling for certain stochastic recursive sequences.
• Perfect Simulation of Conditionally Specified Models
• Sampling-Based Approaches to Calculating Marginal Densities
• Simulation of multivariate normal rectangle probabilities and their derivatives. Theoretical and computational results
• The Method of Simulated Scores for the Estimation of LDV Models

Cited in

(3)

• \(\varepsilon\)-strong simulation of the Brownian path
• Convergence analysis of some multivariate Markov chains using stochastic monotonicity
• Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances

This page was built for publication: One-shot CFTP; application to a class of truncated Gaussian densities

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2433243)