The rate of convergence for approximate Bayesian computation

DOI10.1214/15-EJS988MaRDI QIDQ2259529zbMATHWikidataFDO

Authors S. Barber, Jochen Voss, Mark Webster

Publication date 4 March 2015

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1311.2038

zbMATH Keywords

rate of convergenceapproximate Bayesian computationlikelihood-free inferenceMonte Carlo methodsconvergence of estimators

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Bayesian inference (62F15) Monte Carlo methods (65C05)

Abstract: Approximate Bayesian Computation (ABC) is a popular computational method for likelihood-free Bayesian inference. The term "likelihood-free" refers to problems where the likelihood is intractable to compute or estimate directly, but where it is possible to generate simulated data $X$ relatively easily given a candidate set of parameters $heta$ simulated from a prior distribution. Parameters which generate simulated data within some tolerance $delta$ of the observed data $x^{\ast }$ are regarded as plausible, and a collection of such $heta$ is used to estimate the posterior distribution $heta,|,X!=!x^{\ast }$. Suitable choice of $delta$ is vital for ABC methods to return good approximations to $heta$ in reasonable computational time. While ABC methods are widely used in practice, particularly in population genetics, study of the mathematical properties of ABC estimators is still in its infancy. We prove that ABC estimates converge to the exact solution under very weak assumptions and, under slightly stronger assumptions, quantify the rate of this convergence. Our results can be used to guide the choice of the tolerance parameter $delta$.

Recommendations

• Adaptive approximate Bayesian computation tolerance selection
• Asymptotic properties of approximate Bayesian computation
• New insights into approximate Bayesian computation
• A new approach to choose acceptance cutoff for approximate Bayesian computation
• Approximate Bayesian computational methods

Cites work

• scientific article; zbMATH DE number 1022658 (Why is no real title available?)
• scientific article; zbMATH DE number 1158743 (Why is no real title available?)
• An introduction to statistical computing. A simulation-based approach
• Approximate Bayesian computation: a nonparametric perspective
• Approximate Bayesian computational methods
• Estimation of parameters for macroparasite population evolution using approximate Bayesian computation
• Extreme Points of Moment Sets
• Inference for Stereological Extremes
• New insights into approximate Bayesian computation
• Sequential Monte Carlo without likelihoods
• The rate of convergence for approximate Bayesian computation

Cited in

(27)

• Convergence of regression-adjusted approximate Bayesian computation
• The rate of convergence for approximate Bayesian computation
• An approximate likelihood perspective on ABC methods
• Improving the Accuracy of Marginal Approximations in Likelihood-Free Inference via Localization
• Information geometry for approximate Bayesian computation
• Multilevel rejection sampling for approximate Bayesian computation
• Local dimension reduction of summary statistics for likelihood-free inference
• On the use of approximate Bayesian computation Markov chain Monte Carlo with inflated tolerance and post-correction
• Adaptive approximate Bayesian computation tolerance selection
• Bayesian estimation of agent-based models
• Asymptotic properties of approximate Bayesian computation
• Bayesian mode and maximum estimation and accelerated rates of contraction
• Mutation and selection in bacteria: modelling and calibration
• A new approach to choose acceptance cutoff for approximate Bayesian computation
• A rare event approach to high-dimensional approximate Bayesian computation
• Spectral density-based and measure-preserving ABC for partially observed diffusion processes. An illustration on Hamiltonian SDEs
• \(L^\infty\) metric criteria for convergence in Bayesian recursive inference systems
• Weak convergence of posteriors conditional on maximum pseudo-likelihood estimates and implications in ABC
• Adaptive Gaussian Process Approximation for Bayesian Inference with Expensive Likelihood Functions
• Vector operations for accelerating expensive Bayesian computations - a tutorial guide
• Piecewise approximate Bayesian computation: fast inference for discretely observed Markov models using a factorised posterior distribution
• On predictive inference for intractable models via approximate Bayesian computation
• Bayesian computation: a summary of the current state, and samples backwards and forwards
• A simulated annealing approach to approximate Bayes computations
• Diagnostic tools for approximate Bayesian computation using the coverage property
• Multifidelity approximate Bayesian computation
• A tutorial introduction to Bayesian inference for stochastic epidemic models using approximate Bayesian computation

Describes a project that uses

Uses Software

• R

This page was built for publication: The rate of convergence for approximate Bayesian computation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2259529)