The pseudo-marginal approach for efficient Monte Carlo computations
A powerful and flexible MCMC (Markov chain Monte Carlo) algorithm for stochastic simulation is proposed which builds on pseudo-marginal method originally introduced by \textit{M. A. Beaumont} [Genetics 164, 1139--1160 (2003)]. In the discrete case, it is the following. Given joint probability distribution \(\pi(\theta,z)\) and conditional distribution \(q_\theta(z)\) the goal is to sample from the marginal distribution \(\pi(\theta)\) (\(\theta \in \Theta\), \(z \in Z\)). If \(\pi(\theta)\) is known analitically or cheap to compute, it would be possible to use Metropolis-Hastings algorithm and to generate samples from a Markov chain with transition probabilities \(p(\theta, \theta')=1 \wedge \frac{\pi(\theta')}{\pi(\theta)}\) if \(\theta' \neq \theta\). If it is not the case, it is proposed in the article to replace probabilities \(\pi(\theta)\), \(\pi(\theta')\) with the estinators \[ \overline{\pi}^N(\theta)=\frac{1}{N} \sum_{k=1}^N \frac{\pi(\theta,z(k))}{q_\theta(z(k))}, \quad \overline{\pi}^N(\theta')=\frac{1}{N} \sum_{k=1}^N \frac{\pi(\theta',z'(k))}{q_{\theta'}(z'(k))}, \] where \(z(k)|\theta \sim q_\theta(\cdot)\), \(z'(k)|\theta' \sim q_{\theta'}(\cdot)\), \(k=1,\dots,N\), the data available during the simulation. In the article for rather arbitrary spaces \(\Theta\), \(Z\) theoretical results are given describing the convergence properties of the proposed method, and simple numerical examples are given to illustrate the promising empirical characteristics of the technique. Interesting comparisons with a more obvious, but inexact, Monte Carlo approximations to the marginal algorithm are also given.
- A note on Metropolis-Hastings kernels for general state spaces
- Analyses of Infectious Disease Data from Household Outbreaks by Markov Chain Monte Carlo Methods
- Bayesian variable and link determination for generalised linear models
- Covariance structure of the Gibbs sampler with applications to the comparisons of estimators and augmentation schemes
- Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
- scientific article; zbMATH DE number 1085989 (Why is no real title available?)
- Markov chain Monte Carlo model determination for hierarchical and graphical log-linear models
- Markov chains and stochastic stability
- Monte Carlo statistical methods
- Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
- The correlated pseudomarginal method
- cPseudoMaRg
- An extended empirical saddlepoint approximation for intractable likelihoods
- Some improvements to the Shenoy-Shafer and Hugin architectures for computing marginals
- A Repelling–Attracting Metropolis Algorithm for Multimodality
- Markov chain Monte Carlo with the integrated nested Laplace approximation
- Which ergodic averages have finite asymptotic variance?
- Simulation-based Bayesian inference for epidemic models
- Marginal reversible jump Markov chain Monte Carlo with application to motor unit number estimation
- A transdimensional approximate Bayesian computation using the pseudo-marginal approach for model choice
- Piecewise deterministic Markov processes for continuous-time Monte Carlo
- Modelling and computation using NCoRM mixtures for density regression
- An approximate likelihood perspective on ABC methods
- Bayesian estimation of agent-based models
- Accelerating pseudo-marginal MCMC using Gaussian processes
- Model selection for time series of count data
- Mode jumping MCMC for Bayesian variable selection in GLMM
- Bayesian estimation of state space models using moment conditions
- Efficient importance sampling in low dimensions using affine arithmetic
- Coupling stochastic EM and approximate Bayesian computation for parameter inference in state-space models
- On coupling particle filter trajectories
- Unbiased Bayesian inference for population Markov jump processes via random truncations
- Efficient Bayesian inference for COM-Poisson regression models
- A rare event approach to high-dimensional approximate Bayesian computation
- Variational Bayes with synthetic likelihood
- Barker's algorithm for Bayesian inference with intractable likelihoods
- Efficient MCMC for Gibbs random fields using pre-computation
- MEXIT: maximal un-coupling times for stochastic processes
- Sequential Monte Carlo as approximate sampling: bounds, adaptive resampling via \(\infty\)-ESS, and an application to particle Gibbs
- Extreme value-based methods for modeling elk yearly movements
- X-TMCMC: adaptive kriging for Bayesian inverse modeling
- Fast model-fitting of Bayesian variable selection regression using the iterative complex factorization algorithm
- Many-candidate Nash equilibria for elections involving random selection
- Bayesian estimation of dynamic asset pricing models with informative observations
- On Russian roulette estimates for Bayesian inference with doubly-intractable likelihoods
- A comparison of inferential methods for highly nonlinear state space models in ecology and epidemiology
- Leave Pima Indians alone: binary regression as a benchmark for Bayesian computation
- Model comparison for Gibbs random fields using noisy reversible jump Markov chain Monte Carlo
- Likelihood-free inference in high dimensions with synthetic likelihood
- Partition-weighted Monte Carlo estimation
- A comparative study of Monte Carlo methods for efficient evaluation of marginal likelihood
- Statistical tools for seed bank detection
- Perturbation bounds for Monte Carlo within metropolis via restricted approximations
- f-SAEM: a fast stochastic approximation of the EM algorithm for nonlinear mixed effects models
- Data-cloning SMC\(^2\): a global optimizer for maximum likelihood estimation of latent variable models
- Modeling strength and failure variability due to porosity in additively manufactured metals
- An adaptive MCMC method for Bayesian variable selection in logistic and accelerated failure time regression models
- Making inference of British household's happiness efficiency: a Bayesian latent model
- Pseudo-marginal Bayesian inference for Gaussian process latent variable models
- Efficiency of delayed-acceptance random walk metropolis algorithms
- Particle methods for stochastic differential equation mixed effects models
- Generalized parallel tempering on Bayesian inverse problems
- Product-form estimators: exploiting independence to scale up Monte Carlo
- Full Bayesian inference in hidden Markov models of plant growth
- A subsampling approach for Bayesian model selection
- Comparison of Markov chains via weak Poincaré inequalities with application to pseudo-marginal MCMC
- Augmented pseudo-marginal Metropolis-Hastings for partially observed diffusion processes
- Bayesian estimation of long-run risk models using sequential Monte Carlo
- Gaussian process enhanced semi-automatic approximate Bayesian computation: parameter inference in a stochastic differential equation system for chemotaxis
- Learning nonlinear turbulent dynamics from partial observations via analytically solvable conditional statistics
- A numerically stable algorithm for integrating Bayesian models using Markov melding
- A drift homotopy implicit particle filter method for nonlinear filtering problems
- Randomized approaches to accelerate MCMC algorithms for Bayesian inverse problems
- Jump Markov chains and rejection-free Metropolis algorithms
- Stochastic zeroth-order discretizations of Langevin diffusions for Bayesian inference
- On the theoretical properties of the exchange algorithm
- Exact convergence analysis of the independent Metropolis-Hastings algorithms
- A comparison of likelihood-free methods with and without summary statistics
- Neglected chaos in international stock markets: Bayesian analysis of the joint return-volatility dynamical system
- The node-wise pseudo-marginal method: model selection with spatial dependence on latent graphs
- Penalised t-walk MCMC
- Statistic selection and MCMC for differentially private Bayesian estimation
- Bayesian parameter estimation for the Swift model of eye-movement control during reading
- Unbiased Markov chain Monte Carlo for intractable target distributions
- A flexible particle Markov chain Monte Carlo method
- Random time step probabilistic methods for uncertainty quantification in chaotic and geometric numerical integration
- Accelerating Metropolis-within-Gibbs sampler with localized computations of differential equations
- Likelihood-free approximate Gibbs sampling
- Importance sampling correction versus standard averages of reversible MCMCs in terms of the asymptotic variance
- A framework for adaptive MCMC targeting multimodal distributions
- Characterization of partially observed epidemics through Bayesian inference: application to COVID-19
- A new efficient parameter estimation algorithm for high-dimensional complex nonlinear turbulent dynamical systems with partial observations
- A direct filter method for parameter estimation
- Efficient Bayesian model choice for partially observed processes: with application to an experimental transmission study of an infectious disease
- Counterexamples for optimal scaling of Metropolis-Hastings chains with rough target densities
- Bayesian model discrimination for partially-observed epidemic models
- Endogenous dynamic efficiency in the intertemporal optimization models of firm behavior
- Sequential Monte Carlo with transformations
- Subsampling MCMC -- an introduction for the survey statistician
- Composable models for online Bayesian analysis of streaming data
- Informed sub-sampling MCMC: approximate Bayesian inference for large datasets
- Computationally efficient Bayesian estimation of high-dimensional Archimedean copulas with discrete and mixed margins
- On the efficiency of pseudo-marginal random walk Metropolis algorithms
- Convergence properties of pseudo-marginal Markov chain Monte Carlo algorithms
- On nonnegative unbiased estimators
- Bayesian inference for Markov jump processes with informative observations
- Likelihood free inference for Markov processes: a comparison
- Bayesian semiparametric Wiener system identification
- The use of a single pseudo-sample in approximate Bayesian computation
- Correlated pseudo-marginal schemes for time-discretised stochastic kinetic models
This page was built for publication: The pseudo-marginal approach for efficient Monte Carlo computations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q122160)