Maximin Robust Bayesian Experimental Design

ArXi:2603.14094v1 Announce Type: cross 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 nstrate that this approach yields a robust objective governed by Sibson's $\alpha$-mutual information~(MI), which identifies the $\alpha$-tilted posterior as the robust belief update and establishes the R\'enyi divergence as the appropriate measure of conditional information gain.