An induced natural selection heuristic for finding optimal Bayesian experimental designs

DOI10.1016/J.CSDA.2018.04.011zbMATH Open1469.62130arXiv1703.05511OpenAlexW2605976390WikidataQ62563936 ScholiaQ62563936MaRDI QIDQ1663096FDOQ1663096

J. V. Ross, Nigel G. Bean, Jonathan Tuke, David J. Price

Publication date: 21 August 2018

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Abstract: Bayesian optimal experimental design has immense potential to inform the collection of data so as to subsequently enhance our understanding of a variety of processes. However, a major impediment is the difficulty in evaluating optimal designs for problems with large, or high-dimensional, design spaces. We propose an efficient search heuristic suitable for general optimisation problems, with a particular focus on optimal Bayesian experimental design problems. The heuristic evaluates the objective (utility) function at an initial, randomly generated set of input values. At each generation of the algorithm, input values are "accepted" if their corresponding objective (utility) function satisfies some acceptance criteria, and new inputs are sampled about these accepted points. We demonstrate the new algorithm by evaluating the optimal Bayesian experimental designs for the previously considered death, pharmacokinetic and logistic regression models. Comparisons to the current "gold-standard" method are given to demonstrate the proposed algorithm as a computationally-efficient alternative for moderately-large design problems (i.e., up to approximately 40-dimensions).

Full work available at URL: https://arxiv.org/abs/1703.05511

Recommendations

• Finding near-optimal Bayesian experimental designs via genetic algorithms
• Bayesian-Optimal Design via Interacting Particle Systems
• Towards Bayesian experimental design for nonlinear models that require a large number of sampling times
• Heuristic optimization of experimental designs.
• scientific article; zbMATH DE number 418918

zbMATH Keywords

Bayesian optimal designstochastic modelsoptimisation heuristicsampling windows

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Applications of statistics to biology and medical sciences; meta analysis (62P10) Optimal statistical designs (62K05)

Cites Work

• Title not available (Why is that?)
• On Information and Sufficiency
• Bayesian statistics and the efficiency and ethics of clinical trials
• Optimal design of experimental epidemics
• On the efficient determination of optimal Bayesian experimental designs using ABC: a case study in optimal observation of epidemics
• Optimal Observation Times in Experimental Epidemic Processes
• Title not available (Why is that?)
• Bayesian Experimental Design for Models with Intractable Likelihoods
• A tutorial on the cross-entropy method
• Towards Bayesian experimental design for nonlinear models that require a large number of sampling times

Cited In (6)

• Efficient construction of Bayes optimal designs for stochastic process models
• Modern Bayesian experimental design
• Designing group dose-response studies in the presence of transmission
• Optimal Bayesian design for model discrimination via classification
• Bayesian experimental design without posterior calculations: an adversarial approach
• Sequential Bayesian experimental design for implicit models via mutual information

Uses Software

• acebayes

This page was built for publication: An induced natural selection heuristic for finding optimal Bayesian experimental designs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1663096)