Multimodal Information Gain in Bayesian Design of Experiments

TL;DR

This paper introduces a novel global-local multimodal approach for Bayesian experimental design that efficiently estimates expected information gain in multimodal posterior distributions, overcoming limitations of existing methods.

Contribution

The paper develops a new method combining global search and local Laplace approximations to accurately and efficiently estimate information gain in multimodal posteriors, independent of problem dimension.

Findings

The approach outperforms existing methods in accuracy and efficiency.

It effectively handles multiple modes in posterior distributions.

The method is applicable to experiments with various noise calibrations.

Abstract

One of the well-known challenges in optimal experimental design is how to efficiently estimate the nested integrations of the expected information gain. The Gaussian approximation and associated importance sampling have been shown to be effective at reducing the numerical costs. However, they may fail due to the non-negligible biases and the numerical instabilities. A new approach is developed to compute the expected information gain, when the posterior distribution is multimodal - a situation previously ignored by the methods aiming at accelerating the nested numerical integrations. Specifically, the posterior distribution is approximated using a mixture distribution constructed by multiple runs of global search for the modes and weighted local Laplace approximations. Under any given probability of capturing all the modes, we provide an estimation of the number of runs of searches, which is dimension independent. It is shown that the novel global-local multimodal approach can be significantly more accurate and more efficient than the other existing approaches, especially when the number of modes is large. The methods can be applied to the designs of experiments with both calibrated and uncalibrated observation noises.