Online Program Home
My Program

Abstract Details

Activity Number: 573 - Design of Experiments for Stochastic Process Models
Type: Topic Contributed
Date/Time: Wednesday, August 1, 2018 : 2:00 PM to 3:50 PM
Sponsor: Royal Statistical Society
Abstract #329265 Presentation
Title: Optimal Bayesian Design for Models with Intractable Likelihoods via Machine Learning Methods
Author(s): Christopher C Drovandi and Markus Hainy*
Companies: Queensland University of Technology and QUT
Keywords: experimental design; Bayesian; model selection; machine learning; intractable likelihoods; approximate Bayesian computation

Optimal Bayesian experimental design is often computationally intensive due to the need to approximate many posterior distributions for datasets simulated from the prior predictive distribution. The issues are compounded further when the statistical models of interest do not possess tractable likelihood functions and only simulation is feasible. We adopt machine learning methods like trees and random forests to facilitate the computation of utility values in optimal Bayesian design when the experimental goal is to discriminate between different models.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program