Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design
Abstract
We develop a semi-amortized, policy-based, approach to Bayesian experimental design (BED) called Stepwise Deep Adaptive Design (Step-DAD). Like existing, fully amortized, policy-based BED approaches, Step-DAD trains a design policy upfront before the experiment. However, rather than keeping this policy fixed, Step-DAD periodically updates it as data is gathered, refining it to the particular experimental instance. This test-time adaptation improves both the flexibility and the robustness of the design strategy compared with existing approaches. Empirically, Step-DAD consistently demonstrates superior decision-making and robustness compared with current state-of-the-art BED methods.
Cite
@article{arxiv.2507.14057,
title = {Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design},
author = {Marcel Hedman and Desi R. Ivanova and Cong Guan and Tom Rainforth},
journal= {arXiv preprint arXiv:2507.14057},
year = {2026}
}
Comments
Accepted at Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada. PMLR 267, 2025