A Comparison of Kernels for ABC-SMC

A popular method for likelihood-free inference is approximate Bayesian computation sequential Monte Carlo (ABC-SMC) algorithms. These approximate the posterior using a population of particles, which are updated using Markov kernels. Several such kernels have been proposed. In this paper we review these, highlighting some less well known choices, and proposing some novel options. Further, we conduct an extensive empirical comparison of kernel choices. Our results suggest using a one-hit kernel with a mixture proposal as a default choice.

• Publication year

  2025

• Venue

  Unknown venue

• Publication date

  2025-11-09

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 2511.06351
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Fast, accurate and lightweight sequential simulation-based inference using Gaussian locally linear mappings

  2024cited by this paper
• The Statistical Accuracy of Neural Posterior and Likelihood Estimation

  2024cited by this paper
• Is Learning Summary Statistics Necessary for Likelihood-free Inference?

  2023cited by this paper
• Continual Repeated Annealed Flow Transport Monte Carlo

  2022cited by this paper
• Inferring transmission routes for foot-and-mouth disease virus within a cattle herd using approximate Bayesian computation

  2022cited by this paper
• Summary Statistics

  2022cited by this paper
• Guided Sequential ABC Schemes for Intractable Bayesian Models

  2022cited by this paper
• Annealed Flow Transport Monte Carlo

  2021cited by this paper
• POT: Python Optimal Transport

  2021cited by this paper
• A comparison of likelihood-free methods with and without summary statistics

  2021cited by this paper
• Benchmarking Simulation-Based Inference

  2021cited by this paper
• Normalizing Flows: An Introduction and Review of Current Methods

  2020cited by this paper
• A Review of Multi‐Compartment Infectious Disease Models

  2020cited by this paper
• Waste‐free sequential Monte Carlo

  2020cited by this paper
• Distilling Importance Sampling for Likelihood Free Inference

  2019cited by this paper
• Approximate Bayesian Computation

  2019cited by this paper
• Neural Spline Flows

  2019cited by this paper
• Approximate Bayesian computation with the Wasserstein distance

  2019influential reference
• Normalizing Flows for Probabilistic Modeling and Inference

  2019cited by this paper
• Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flows

  2018cited by this paper
• ABC Samplers

  2018cited by this paper
• Negative association, ordering and convergence of resampling methods

  2017cited by this paper
• Delayed Acceptance ABC-SMC

  2017cited by this paper
• Fast ε-free Inference of Simulation Models with Bayesian Conditional Density Estimation

  2016cited by this paper
• Robust Bayesian Inference via Coarsening

  2015cited by this paper
• Adapting the ABC distance function

  2015cited by this paper
• Accelerating Metropolis-Hastings algorithms by Delayed Acceptance

  2015cited by this paper
• On Bayesian inference for the M/G/1 queue with efficient MCMC sampling

  2014cited by this paper
• On the convergence of adaptive sequential Monte Carlo methods

  2013influential reference
• Inference for SDE Models via Approximate Bayesian Computation

  2012cited by this paper
• On the choice of MCMC kernels for approximate Bayesian computation with SMC samplers

  2012influential reference
• Variance bounding and geometric ergodicity of Markov chain Monte Carlo kernels for approximate Bayesian computation

  2012cited by this paper
• An adaptive sequential Monte Carlo method for approximate Bayesian computation

  2011influential reference
• Likelihood-Free MCMC

  2011influential reference
• Approximate Bayesian computational methods

  2011cited by this paper
• On the stability of sequential Monte Carlo methods in high dimensions

  2011cited by this paper
• On optimality of kernels for approximate Bayesian computation using sequential Monte Carlo

  2011cited by this paper
• Sequential Monte Carlo Samplers: Error Bounds and Insensitivity to Initial Conditions

  2011cited by this paper
• Particle Markov chain Monte Carlo methods

  2010cited by this paper
• Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems

  2009cited by this paper
• Optimal Transport: Old and New

  2008cited by this paper
• Adaptive approximate Bayesian computation

  2008cited by this paper
• Approximate Bayesian computation (ABC) gives exact results under the assumption of model error

  2008cited by this paper
• Sequential Monte Carlo without likelihoods

  2007cited by this paper
• Markov chain Monte Carlo without likelihoods

  2003cited by this paper
• Sequential Monte Carlo samplers

  2002cited by this paper
• Improved particle filter for nonlinear problems

  1999cited by this paper
• Rates of convergence of the Hastings and Metropolis algorithms

  1996cited by this paper
• Weighted Average Importance Sampling and Defensive Mixture Distributions

  1995cited by this paper

• No citing papers are available for this paper.