Finding our way in the dark: approximate MCMC for approximate Bayesian methods
From MaRDI portal
Abstract: With larger data at their disposal, scientists are emboldened to tackle complex questions that require sophisticated statistical models. It is not unusual for the latter to have likelihood functions that elude analytical formulations. Even under such adversity, when one can simulate from the sampling distribution, Bayesian analysis can be conducted using approximate methods such as Approximate Bayesian Computation (ABC) or Bayesian Synthetic Likelihood (BSL). A significant drawback of these methods is that the number of required simulations can be prohibitively large, thus severely limiting their scope. In this paper we design perturbed MCMC samplers that can be used within the ABC and BSL paradigms to significantly accelerate computation while maintaining control on computational efficiency. The proposed strategy relies on recycling samples from the chain's past. The algorithmic design is supported by a theoretical analysis while practical performance is examined via a series of simulation examples and data analyses.
Recommendations
- Multilevel rejection sampling for approximate Bayesian computation
- Efficient acquisition rules for model-based approximate Bayesian computation
- An approximate likelihood perspective on ABC methods
- Approximate Bayesian computation with differential evolution
- Improved approximate Bayesian computation methods via empirical likelihood
Cites work
- A one-pass sequential Monte Carlo method for Bayesian analysis of massive datasets
- Accelerating pseudo-marginal MCMC using Gaussian processes
- An Algorithm for Finding Best Matches in Logarithmic Expected Time
- An overview on Approximate Bayesian computation
- Approximate Bayesian computational methods
- Bayesian Synthetic Likelihood
- Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation. With discussion and authors' reply
- Convergence Properties of Perturbed Markov Chains
- Convergence properties of pseudo-marginal Markov chain Monte Carlo algorithms
- Efficient acquisition rules for model-based approximate Bayesian computation
- Efficient MCMC for Gibbs random fields using pre-computation
- Gaussian Markov Random Fields
- Handbook of approximate Bayesian computation
- Handbook of Markov Chain Monte Carlo
- Lectures on the nearest neighbor method
- Likelihood inflating sampling algorithm
- Multidimensional binary search trees used for associative searching
- Of copulas, quantiles, ranks and spectra: an \(L_{1}\)-approach to spectral analysis
- Optimal scaling for various Metropolis-Hastings algorithms.
- Particle Markov chain Monte Carlo for efficient numerical simulation
- QUANTILE CORRELATIONS: UNCOVERING TEMPORAL DEPENDENCIES IN FINANCIAL TIME SERIES
- Rates of convergence of the Hastings and Metropolis algorithms
- Relevant statistics for Bayesian model choice
- Robust Bayesian synthetic likelihood via a semi-parametric approach
- Sensitivity and convergence of uniformly ergodic Markov chains
- Sequential Monte Carlo without likelihoods
- Speeding Up MCMC by Efficient Data Subsampling
- Statistical analysis of network data with R
- Strong consistency of nearest neighbor regression function estimators
- The pseudo-marginal approach for efficient Monte Carlo computations
- VOLATILITY CLUSTERING IN FINANCIAL MARKETS: A MICROSIMULATION OF INTERACTING AGENTS
- Weak convergence and optimal scaling of random walk Metropolis algorithms
This page was built for publication: Finding our way in the dark: approximate MCMC for approximate Bayesian methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6121616)
