Publications etc

Below are my “main” publications. I’ve left out a few things where I’m a minor coauthor. For a complete list see my google scholar page. Please email me for copies of anything below that you cannot access.

Papers

2023

• Distilling importance sampling for likelihood-free inference
  Journal of Computational and Graphical Statistics (to appear)
  Dennis Prangle and Cecilia Viscardi
  

2022

• Bayesian experimental design without posterior calculations: an adversarial approach
  Bayesian Analysis
  Sophie Harbisher, Colin S. Gillespie, Dennis Prangle

2021

• Emulating computer experiments of transport infrastructure slope stability using Gaussian processes and Bayesian inference
  Data Centric Engineering
  Aleksandra Svalova, Peter Helm, Dennis Prangle, Mohamed Rouainia, Stephanie Glendinning, Darren J Wilkinson

• The neural moving average model for scalable variational inference of state space models
  Uncertainty in Artificial Intelligence
  Tom Ryder, Andrew Golightly, Isaac Matthews, Dennis Prangle

• Ensemble MCMC: Accelerating pseudo-marginal MCMC for state space models using the ensemble Kalman filter
  Bayesian Analysis
  Chris Drovandi, Richard Everitt, Andrew Golightly, Dennis Prangle

• Measure transport with kernel Stein discrepancy
  Intenational Conference on Artificial Intelligence and Statistics
  Matthew Fisher, Tui Nolan, Matthew Graham, Dennis Prangle, Chris J Oates

2020

• Black-box inference for non-linear latent force models
  Intenational Conference on Artificial Intelligence and Statistics
  Wil O. C. Ward, Tom Ryder, Dennis Prangle, Mauricio A. Álvarez

• gk: An R Package for the g-and-k and generalised g-and-h distributions
  The R Journal
  Dennis Prangle

2019

• Optimality criteria for probabilistic numerical methods
  RICAM workshop proceedings
  Chris. J. Oates, Jon Cockayne, Dennis Prangle, T.J. Sullivan, Mark Girolami

2018

• Black-box autoregressive density estimation for state-space models
  Thomas Ryder, Andrew Golighty, A. Stephen McGough, Dennis Prangle
  • NeurIPS workshop paper

• Recalibration: A post-processing method for approximate Bayesian computation
  Computational Statistics & Data Analysis
  Guilherme Rodrigues, Dennis Prangle, Scott Sisson

• Summary statistics in Approximate Bayesian Computation
  Chapter in the Handbook of ABC, edited by S. Sisson, Y. Fan, and M. Beaumont
  Dennis Prangle

• Black-box variational inference for stochastic differential equations
  International Conference on Machine Learning
  Thomas Ryder, Andrew Golightly, A. Stephen McGough, Dennis Prangle
  

• Taking error into account when fitting models using Approximate Bayesian Computation
  Ecological Applications
  Elske van der Vaart, Dennis Prangle, Richard M. Sibly

• A rare event approach to high dimensional Approximate Bayesian computation
  Statistics and Computing
  Dennis Prangle, Richard G. Everitt, Theodore Kypraios
  • See also the supporting code.

2017

• Adapting the ABC distance function Bayesian Analysis
  Dennis Prangle
  • See also the code used in the paper.
    
• A tutorial introduction to Bayesian inference for stochastic epidemic models using Approximate Bayesian Computation
  Mathematical Biosciences
  Theodore Kypraios, Peter Neal and Dennis Prangle
  • See also the supporting code.

2016

• An ABC interpretation of the multiple auxiliary variable method
  Dennis Prangle and Richard G. Everitt
  • Technical report
• Lazy ABC
  Statistics and Computing
  Dennis Prangle
  • See also blog post, example code and summary paper “Lazier ABC”.

2015

• abctools: an R package for tuning approximate Bayesian computation analyses
  The R Journal
  Matthew Nunes and Dennis Prangle

• The identification of individuals of advanced age using degeneration of the sternal end of the clavicle
  American journal of physical anthropology
  Ceri G. Falys and Dennis Prangle

2014

• Lazier ABC Contributed NeurIPS workshop paper
  Dennis Prangle
  • Short 5 page paper summarising “Lazy ABC” plus some extensions.
  • This link is slightly more up to date than the arXiv version.
• Diagnostic tools of approximate Bayesian computation using the coverage property
  Australian & New Zealand Journal of Statistics
  Dennis Prangle, Micheal Blum, Gordana Popovic, Scott Sisson
  • Methods implemented by the abctools R package (see below).
• Semi-automatic selection of summary statistics for ABC model choice
  Statistical Applications in Genetics and Molecular Biology
  Dennis Prangle, Paul Fearnhead, Murray P. Cox, Patrick J. Biggs, Nigel P. French

2013

• A comparative review of dimension reduction methods in approximate Bayesian computation
  Statistical Science
  Micheal Blum, Matt Nunes, Dennis Prangle, Scott Sisson

2012

• Constructing summary statistics for approximate Bayesian computation: semi-automatic ABC
  Journal of the Royal Statistical Society Series B
  Paul Fearnhead, Dennis Prangle
  • See my thesis below for supplementary material.

2011

• Summary statistics and sequential methods for approximate Bayesian computation
  PhD thesis
  Dennis Prangle
  • Version without hyperlinks.
    

Software packages

• abctools R package for tuning ABC analyses. Available on CRAN or github. Co-authored with Matt Nunes.

  • The package implements (1) methods to choose summary statistics (2) coverage property diagnostics.
  • See above for a 2015 R Journal paper explaining typical usage.

• gk R package for the g-and-k and generalised g-and-h distributions. Available on CRAN or github. A related paper is now available.

Talks and posters

• A rare event approach to high dimensional ABC
  Video from BIRS workshop (2017).
• Approximate Bayesian computation
  Slides from IBS tutorial, giving a general overview of ABC (2014).
• Advances in approximate Bayesian computation for modelling biological data
  Slides from IBC conference, covering ABC model choice (2014).
• Lazy ABC
  Video and slides from Isaac Newton Institute workshop (2014).
• Constructing ABC summary statistics: semi-automatic ABC
  Slides from ABC in London meeting (2011).
• Faster R code using C
  Presentation material (2010)
  • Only of historical interest, but still occasionally a handy reference for myself!
  • Better options like Rccp are available now.