Perfect sampling for Gibbs point processes using partial rejection sampling

DOI10.3150/19-BEJ1184MaRDI QIDQ2174993zbMATH OpenFDO

Authors Sarat B. Moka, Dirk P. Kroese

Publication date 27 April 2020

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1901.05624, https://projecteuclid.org/euclid.bj/1587974534

zbMATH Keywords

Strauss processpairwise interaction processperfect samplinghard-core processarea-interaction processpartial-rejection samplingpenetrable spheres mixture model

Mathematics Subject Classification ID

Exact distribution theory in statistics (62E15) Point processes (e.g., Poisson, Cox, Hawkes processes) (60G55) Sampling theory, sample surveys (62D05) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Sample path properties (60G17) Lattice systems (Ising, dimer, Potts, etc.) and systems on graphs arising in equilibrium statistical mechanics (82B20)

Abstract: We present a perfect sampling algorithm for Gibbs point processes, based on the partial rejection sampling of Guo et al. (2017). Our particular focus is on pairwise interaction processes, penetrable spheres mixture models and area-interaction processes, with a finite interaction range. For an interaction range $2r$ of the target process, the proposed algorithm can generate a perfect sample with $O(log(1/r))$ expected running time complexity, provided that the intensity of the points is not too high.

Recommendations

• Perfect simulation of some point processes for the impatient user
• Publication:4720048
• A primer on perfect simulation for spatial point processes
• Perfect simulation for interacting point processes, loss networks and Ising models.
• Perfect simulation of spatial processes.

Cites work

• scientific article; zbMATH DE number 1188967 (Why is no real title available?)
• scientific article; zbMATH DE number 1912119 (Why is no real title available?)
• An efficient Markov chain Monte Carlo method for distributions with intractable normalising constants
• An interruptible algorithm for perfect sampling via Markov chains
• Approximation via correlation decay when strong spatial mixing fails
• Area-interaction point processes
• Bayesian Analysis of Markov Point Processes
• Bounds on the artificial phase transition for perfect simulation of hard core Gibbs processes
• Fast approximation of the intensity of Gibbs point processes
• On Local Distributed Sampling and Counting
• Perfect simulation for interacting point processes, loss networks and Ising models.
• Perfect simulation of spatial processes.
• Perfect simulation of the hard disks model by partial rejection sampling
• Perfect simulation using dominating processes on ordered spaces, with application to locally stable point processes
• Rejection- and importance-sampling-based perfect simulation for Gibbs hard-sphere models
• Spatial birth-death swap chains
• Stochastic geometry and its applications
• Uniform sampling through the Lovász local lemma
• What Can be Sampled Locally?

Cited in

(8)

• Rejection- and importance-sampling-based perfect simulation for Gibbs hard-sphere models
• Gaps and interleaving of point processes in sampling from a residual allocation model
• scientific article; zbMATH DE number 5954259 (Why is no real title available?)
• Developments in perfect simulation of Gibbs measures through a new result for the extinction of Galton-Watson-like processes
• Fundamentals of partial rejection sampling
• Perfect simulation of the hard disks model by partial rejection sampling
• Perfect simulation of the hard disks model by partial rejection sampling
• Quasipolynomial-time algorithms for Gibbs point processes

Describes a project that uses

Uses Software

• spatstat

This page was built for publication: Perfect sampling for Gibbs point processes using partial rejection sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2174993)