A Likelihood-Free Approach to Goal-Oriented Bayesian Optimal Experimental Design
Not on the map. Why?
Abstract (arXiv)
Conventional Bayesian optimal experimental design seeks to maximize the expected information gain (EIG) on model parameters. However, the end goal of the experiment often is not to learn the model parameters, but to predict downstream quantities of interest (QoIs) that depend on the learned parameters. And designs that offer high EIG for parameters may not translate to high EIG for QoIs. Goal-oriented optimal experimental design (GO-OED) thus directly targets to maximize the EIG of QoIs. We introduce LF-GO-OED (likelihood-free goal-oriented optimal experimental design), a computational method for conducting GO-OED with nonlinear observation and prediction models. LF-GO-OED is specifically designed to accommodate implicit models, where the likelihood is intractable. In particular, it builds a density ratio estimator from samples generated from approximate Bayesian computation (ABC), thereby sidestepping the need for likelihood evaluations or density estimations. The overall method is validated on benchmark problems with existing methods, and demonstrated on scientific applications of epidemiology and neural science.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 55 references that are in the map. First posted on arXiv 18 Aug 2024.
Builds on
20 of 55 references.
References · 20
- 2019The frontier of simulation-based inferencecited by 490
- 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 217
- 2023Modern Bayesian Experimental Designcited by 121
- 2019Variational Bayesian Optimal Experimental Designcited by 116
- 2015Approximating Likelihood Ratios with Calibrated Discriminative Classifierscited by 87
- 2016Likelihood-free inference by ratio estimationcited by 80
- 2021Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoodscited by 61
- 2018Mining gold from implicit models to improve likelihood-free inferencecited by 60
- 2020Bayesian Experimental Design for Implicit Models by Mutual Information Neural Estimationcited by 56
- 2024Optimal experimental design: Formulations and computationscited by 45
- 2018Efficient Bayesian Experimental Design for Implicit Modelscited by 34
- 2023Bayesian Synthetic Likelihoodcited by 29
8 more
- 2021Gradient-based Bayesian Experimental Design for Implicit Models using Mutual Information Lower Boundscited by 26
- 2019Efficient MCMC Sampling with Dimension-Free Convergence Rate using ADMM-type Splittingcited by 22
- 2018Goal-Oriented Optimal Design of Experiments for Large-Scale Bayesian Linear Inverse Problemscited by 19
- 2020Parameter Estimation with Dense and Convolutional Neural Networks Applied to the FitzHugh-Nagumo ODEcited by 19
- 2018Sequential Neural Methods for Likelihood-free Inferencecited by 11
- 2018Bayesian design of experiments for intractable likelihood models using coupled auxiliary models and multivariate emulationcited by 10
- 2023Variational Sequential Optimal Experimental Design using Reinforcement Learningcited by 8
- 2024Goal-Oriented Bayesian Optimal Experimental Design for Nonlinear Models using Markov Chain Monte Carlocited by 8
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.