Maximin Robust Bayesian Experimental Design
You are an author of this paper, . Is this page accurate?
You approved this page.
Thanks. We will fix this and let you know.
Lists
Only you see this
Abstract
We address the brittleness of Bayesian experimental design under model misspecification by formulating the problem as a max--min game between the experimenter and an adversarial nature subject to information-theoretic constraints. We demonstrate that this approach yields a robust objective governed by Sibson's $α$-mutual information (MI), which identifies the $α$-tilted posterior as the robust belief update and establishes the Rényi divergence as the appropriate measure of conditional information gain. To mitigate the bias and variance of nested Monte Carlo estimators needed to estimate Sibson's $α$-MI, we adopt a PAC-Bayes framework to search over stochastic design policies, yielding rigorous high-probability lower bounds on the robust expected information gain that explicitly control finite-sample error.
BibTeX
@misc{abdulsamad2026maximin,
author = {Hany Abdulsamad and Sahel Iqbal and Christian A. Naesseth and Takuo Matsubara and Adrien Corenflos},
title = {{Maximin Robust Bayesian Experimental Design}},
year = {2026},
eprint = {2603.14094},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2603.14094},
}Loading related content...