stat.MLNov 8, 2026

Amortized Bayesian Experimental Design with In-Context Knowledge Conditioning

Authors: Zhanghu Zhao, Daolang Huang, Xinyi Wen, Samuel Kaski

Organizations: ELLIS Institute Finland · Department of Computer Science, Aalto University, Finland · Department of Computer Science, University of Helsinki, Finland · Department of Computer Science, University of Manchester, UK

Abstract

Amortized Bayesian experimental design (BED) enables real-time design strategies by shifting acquisition cost offline, but existing methods remain tied to the prior and task distribution they were trained on and cannot exploit additional information available at deployment. We introduce in-context amortized BED with unified knowledge encoding (IMBUE), a BED framework that admits external knowledge at deployment through a unified in-context interface. IMBUE accepts two forms of such knowledge without retraining, namely user-specified prior knowledge and observations from previous instances of the experiment. Both are encoded as additional input tokens and processed in-context with the accumulated observations by a shared Transformer, and a learned reliability filter scores each external token against the observations and excludes inconsistent ones. Across four benchmarks, IMBUE accelerates early-stage information acquisition when the external knowledge is reliable, and remains close to the no-external baseline when it is not.

Figures & tables

Appendix figures & tables32 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Constrained Bayesian Experimental Design via Online Planning

    May 26, 2026Yujia Guo, Daolang Huang, Xinyu Zhang +3Bayesian Experimental DesignSequential Experimental Design

  2. Action-BED: Task-Driven Bayesian Experimental Design with Singly Intractable Objectives

    Jun 22, 2026Tom Rossa, Angus Phillips, Tom RainforthBayesian Decision TheoryBayesian Experimental Design