On parallel implementation of sequential Monte Carlo methods: the island particle model
From MaRDI portal
(Redirected from Publication:5962737)
Abstract: The approximation of the Feynman-Kac semigroups by systems of interacting particles is a very active research field, with applications in many different areas. In this paper, we study the parallelization of such approximations. The total population of particles is divided into sub-populations, referred to as emph{islands}. The particles within each island follow the usual selection / mutation dynamics. We show that the evolution of each island is also driven by a Feynman-Kac semigroup, whose transition and potential can be explicitly related to ones of the original problem. Therefore, the same genetic type approximation of the Feynman-Kac semi-group may be used at the island level; each island might undergo selection / mutation algorithm. We investigate the impact of the population size within each island and the number of islands, and study different type of interactions. We find conditions under which introducing interactions between islands is beneficial. The theoretical results are supported by some Monte Carlo experiments.
Recommendations
- Convergence properties of weighted particle islands with application to the double bootstrap algorithm
- Parallel and interacting Markov chain Monte Carlo algorithm
- Parallelizing particle filters with butterfly interactions
- Interacting sequential Monte Carlo samplers for trans-dimensional simulation
- On the role of interaction in sequential Monte Carlo algorithms
Cites work
- scientific article; zbMATH DE number 2106098 (Why is no real title available?)
- A sequential particle filter method for static models
- Adaptive sequential posterior simulators for massively parallel computing environments
- Blind Deconvolution via Sequential Imputations
- Interacting sequential Monte Carlo samplers for trans-dimensional simulation
- Limit theorems for weighted samples with applications to sequential Monte Carlo methods
- Monte Carlo strategies in scientific computing
- On adaptive resampling strategies for sequential Monte Carlo methods
- Sequential Monte Carlo Methods in Practice
- \(\mathrm{SMC}^2\): an efficient algorithm for sequential analysis of state space models
Cited in
(20)- Parallelization of a dynamic Monte Carlo algorithm: A partially rejection-free conservative approach
- Parallel sequential Monte Carlo for stochastic gradient-free nonconvex optimization
- Finite-sample complexity of sequential Monte Carlo estimators
- A method for high-dimensional smoothing
- Compressed Monte Carlo with application in particle filtering
- An Invitation to Sequential Monte Carlo Samplers
- Sequential Bayesian inference for implicit hidden Markov models and current limitations
- Theory of segmented particle filters
- An ergodic theorem for the weighted ensemble method
- Sequential ensemble transform for Bayesian inverse problems
- Learning undirected graphical models using persistent sequential Monte Carlo
- On the role of interaction in sequential Monte Carlo algorithms
- Generalized Bayesian multidimensional scaling and model comparison
- The Wigner branching random walk: efficient implementation and performance evaluation
- Parallel generalized elliptical slice sampling with adaptive regional pseudo-priors
- A pseudo-marginal sequential Monte Carlo algorithm for random effects models in Bayesian sequential design
- Inference on high-dimensional implicit dynamic models using a guided intermediate resampling filter
- A stable particle filter for a class of high-dimensional state-space models
- Forest resampling for distributed sequential Monte Carlo
- Point process-based Monte Carlo estimation
This page was built for publication: On parallel implementation of sequential Monte Carlo methods: the island particle model
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5962737)
