Robust Bayesian Decision Making under Adversarial Uncertainty
For practitioners in scientific fields where experimental outcomes are subject to unmodeled perturbations, this work provides a method to obtain more reliable decisions, though the improvement is incremental over existing decision-aware design.
The paper addresses the problem of decision-aware experimental design that is robust to hidden or weakly modeled effects. It proposes a Bayesian criterion targeting decision stability, showing that their robustness-aware approach yields significantly more stable and reliable decisions under adversarial variation compared to conventional methods.
Scientific experiments are often designed to maximize information gain, yet in many applications the primary objective is to support reliable downstream decision-making. Existing decision-aware experimental design and active learning methods typically assume well-specified outcome models and implicitly rely on the stability of the optimal decision under real-world perturbations. In practice, however, experimental outcomes are frequently influenced by hidden or weakly modeled effects, which can substantially alter decision optimality and lead to misleading conclusions. We study sequential adversarially robust decision-aware experimental design, where data acquisition has to take into account information gain against plausible worst-case unexpected effects, modeled here as variation in adversarial variables. Building on Bayesian decision theory, we formalize an adversarially robust optimal decision under this setting and derive a principled Bayesian experimental design criterion. The criterion explicitly targets decision stability rather than nominal optimality. Experiments on synthetic and real-world scientific datasets show that conventional decision-aware design can converge rapidly to high confidence yet fragile decisions, while our robustness-aware approach yields decisions that are significantly more stable and reliable under adversarial variation.