On adaptive resampling strategies for sequential Monte Carlo methods
From MaRDI portal
Publication:408101
DOI10.3150/10-BEJ335zbMATH Open1236.60072arXiv1203.0464OpenAlexW2950543536WikidataQ55951932 ScholiaQ55951932MaRDI QIDQ408101FDOQ408101
Authors: Pierre Del Moral, Ajay Jasra, Arnaud Doucet 
Publication date: 29 March 2012
Published in: Bernoulli (Search for Journal in Brave)
Abstract: Sequential Monte Carlo (SMC) methods are a class of techniques to sample approximately from any sequence of probability distributions using a combination of importance sampling and resampling steps. This paper is concerned with the convergence analysis of a class of SMC methods where the times at which resampling occurs are computed online using criteria such as the effective sample size. This is a popular approach amongst practitioners but there are very few convergence results available for these methods. By combining semigroup techniques with an original coupling argument, we obtain functional central limit theorems and uniform exponential concentration estimates for these algorithms.
Full work available at URL: https://arxiv.org/abs/1203.0464
Recommendations
- An adaptive sequential Monte Carlo sampler
- On the convergence of adaptive sequential Monte Carlo methods
- Stratification and optimal resampling for sequential Monte Carlo
- Sequential Monte Carlo as approximate sampling: bounds, adaptive resampling via \(\infty\)-ESS, and an application to particle Gibbs
- Independent Resampling Sequential Monte Carlo Algorithms
- An adaptive sequential Monte Carlo method for approximate Bayesian computation
- Stopping-Time Resampling for Sequential Monte Carlo Methods
- Adaptive strategy for stratified Monte Carlo sampling
- A framework for adaptive Monte Carlo procedures
- On adaptive Markov chain Monte Carlo algorithms
Cites Work
- Sequential Monte Carlo Methods in Practice
- Inference in hidden Markov models.
- Title not available (Why is that?)
- Blind Deconvolution via Sequential Imputations
- Monte Carlo strategies in scientific computing
- Limit theorems for weighted samples with applications to sequential Monte Carlo methods
- Title not available (Why is that?)
Cited In (57)
- Fast and Numerically Stable Particle-Based Online Additive Smoothing: The AdaSmooth Algorithm
- Combined use of importance weights and resampling weights in sequential Monte Carlo methods
- Adaptive online variance estimation in particle filters: the ALVar estimator
- Sequential Kalman tuning of the \(t\)-preconditioned Crank-Nicolson algorithm: efficient, adaptive and gradient-free inference for Bayesian inverse problems
- Unbiased and multilevel methods for a class of diffusions partially observed via marked point processes
- Limit theorems for weighted samples with applications to sequential Monte Carlo methods
- On the Hill relation and the mean reaction time for metastable processes
- Stopping-Time Resampling for Sequential Monte Carlo Methods
- A Wasserstein coupled particle filter for multilevel estimation
- Residual and stratified branching particle filters
- An adaptive sequential Monte Carlo method for approximate Bayesian computation
- Filtering via approximate Bayesian computation
- An Invitation to Sequential Monte Carlo Samplers
- Adaptive particle allocation in iterated sequential Monte Carlo via approximating meta-models
- Free energy computations by minimization of Kullback-Leibler divergence: An efficient adaptive biasing potential method for sparse representations
- Sequential Bayesian inference for vector autoregressions with stochastic volatility
- Distributed navigation system for uniaxial wheeled modules
- Adapting the Number of Particles in Sequential Monte Carlo Methods Through an Online Scheme for Convergence Assessment
- A Bayesian mixture of Lasso regressions with \(t\)-errors
- Gaussian process hyper-parameter estimation using parallel asymptotically independent Markov sampling
- Delayed Acceptance ABC-SMC
- On the stability of sequential Monte Carlo methods in high dimensions
- Variance estimation in adaptive sequential Monte Carlo
- On the role of interaction in sequential Monte Carlo algorithms
- On the convergence of adaptive sequential Monte Carlo methods
- A Particle Method for Solving Fredholm Equations of the First Kind
- Likelihood-free Bayesian estimation of multivariate quantile distributions
- A cautionary tale on the efficiency of some adaptive Monte Carlo schemes
- Optimisation of interacting particle systems for rare event estimation
- Fluctuations, stability and instability of a distributed particle filter with local exchange
- Multilevel particle filters for the non-linear filtering problem in continuous time
- Multilevel sequential Monte Carlo: Mean square error bounds under verifiable conditions
- Particle methods: An introduction with applications
- Static-parameter estimation in piecewise deterministic processes using particle Gibbs samplers
- Improving SAMC using smoothing methods: Theory and applications to Bayesian model selection problems
- Central limit theorems for coupled particle filters
- Sequential Monte Carlo methods for option pricing
- Adaptive sequential Monte Carlo by means of mixture of experts
- Unbiased estimation of the solution to Zakai's equation
- Sequentially adaptive Bayesian learning algorithms for inference and optimization
- A stable particle filter for a class of high-dimensional state-space models
- Feynman-Kac Particle Integration with Geometric Interacting Jumps
- Stability properties of some particle filters
- Error Bounds and Normalising Constants for Sequential Monte Carlo Samplers in High Dimensions
- Multilevel Particle Filters
- Sequential Monte Carlo Samplers: Error Bounds and Insensitivity to Initial Conditions
- Quantitative approximations of evolving probability measures and sequential Markov chain Monte Carlo methods
- On parallel implementation of sequential Monte Carlo methods: the island particle model
- Parameter Estimation for Hidden Markov Models with Intractable Likelihoods
- A coherent structure approach for parameter estimation in Lagrangian data assimilation
- Inference for a class of partially observed point process models
- A simple numerical method based simultaneous stochastic perturbation for estimation of high dimensional matrices
- Multimodal, high-dimensional, model-based, Bayesian inverse problems with applications in biomechanics
- Linear variance bounds for particle approximations of time-homogeneous Feynman-Kac formulae
- On the foundations and the applications of evolutionary computing
- Efficient particle filtering for stochastic Korteweg–de Vries equations
- Multilevel sequential Monte Carlo samplers
This page was built for publication: On adaptive resampling strategies for sequential Monte Carlo methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q408101)
