mlsanityData to 7 Oct 2026

Constrained Bayesian Experimental Design via Online Planning

arXiv 2605.26990 ↗First posted 26 May 2026stat.ML cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Bayesian experimental design (BED) is a principled framework for data-efficient design of sequential experiments. However, existing BED methods are unable to adapt to dynamic constraints inherent in real-world tasks due to budget limitations, varying costs, or physical constraints that restrict how designs evolve over time. In this paper, we introduce a novel approach to BED that enables constrained optimization of experimental designs by combining offline pre-training of an amortized policy and a posterior network with online multi-step lookahead planning using scenario trees. We empirically demonstrate that our method yields substantially more informative design sequences than existing methods across a range of constrained BED tasks, while incurring only a modest additional computational overhead.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 44 of its 77 references that are in the map. First posted on arXiv 26 May 2026.

Builds on

44 of 77 references.

References · 44

  1. 2016Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Roboticscited by 134
  2. 2022Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modelingcited by 126
  3. 2023Modern Bayesian Experimental Designcited by 121
  4. 2019Variational Bayesian Optimal Experimental Designcited by 116
  5. 2021Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Designcited by 103
  6. 2023Flow Matching for Scalable Simulation-Based Inferencecited by 97
  7. 2017On Nesting Monte Carlo Estimatorscited by 82
  8. 2018Stagewise Safe Bayesian Optimization with Gaussian Processescited by 79
  9. 2015Bayesian optimization for materials designcited by 78
  10. 2021Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoodscited by 61
  11. 2023Prediction-Oriented Bayesian Active Learningcited by 60
  12. 2019A Unified Stochastic Gradient Approach to Designing Bayesian-Optimal Experimentscited by 58
32 more
  1. 2020Bayesian Experimental Design for Implicit Models by Mutual Information Neural Estimationcited by 56
  2. 2023Learning Robust Statistics for Simulation-based Inference under Model Misspecificationcited by 48
  3. 2022Optimizing Sequential Experimental Design with Deep Reinforcement Learningcited by 45
  4. 2020Cost-aware Bayesian Optimizationcited by 41
  5. 2020Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Treescited by 41
  6. 2019BINOCULARS for Efficient, Nonmyopic Sequential Experimental Designcited by 35
  7. 2018Efficient Bayesian Experimental Design for Implicit Modelscited by 34
  8. 2016Sequential Bayesian optimal experimental design via approximate dynamic programmingcited by 27
  9. 2020Sequential Bayesian Experimental Design for Implicit Models via Mutual Informationcited by 23
  10. 2024Amortized Probabilistic Conditioning for Optimization, Simulation and Inferencecited by 22
  11. 2024Amortized Bayesian Experimental Design for Decision-Makingcited by 20
  12. 2020Efficient Rollout Strategies for Bayesian Optimizationcited by 19
  13. 2018HyP-DESPOT: A Hybrid Parallel Algorithm for Online Planning under Uncertaintycited by 18
  14. 2021A Nonmyopic Approach to Cost-Constrained Bayesian Optimizationcited by 18
  15. 2021Multi-Step Budgeted Bayesian Optimization with Unknown Evaluation Costscited by 18
  16. 2024Cost-aware Bayesian Optimization via the Pandora's Box Gittins Indexcited by 16
  17. 2022Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Modelscited by 15
  18. 2022Safe Active Learning for Multi-Output Gaussian Processescited by 13
  19. 2024Safe Active Learning for Time-Series Modeling with Gaussian Processescited by 12
  20. 2024Nesting Particle Filters for Experimental Design in Dynamical Systemscited by 12
  21. 2025Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Designcited by 12
  22. 2019Cost-aware Multi-objective Bayesian optimisationcited by 8
  23. 2023Variational Sequential Optimal Experimental Design using Reinforcement Learningcited by 8
  24. 2025ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisitioncited by 8
  25. 2019Informative Path Planning for Active Field Mapping under Localization Uncertaintycited by 6
  26. 2024Cost-aware simulation-based inferencecited by 6
  27. 2013Information Acquisition with Sensing Robots: Algorithms and Error Boundscited by 5
  28. 2023Statistically Efficient Bayesian Sequential Experiment Design via Reinforcement Learning with Cross-Entropy Estimatorscited by 5
  29. 2024PASOA- PArticle baSed Bayesian Optimal Adaptive designcited by 5
  30. 2021Online Informative Path Planning for Active Information Gathering of a 3D Surfacecited by 3
  31. 2025Amortized Safe Active Learning for Real-Time Data Acquisition: Pretrained Neural Policies From Simulated Nonparametric Functionscited by 3
  32. 2025Representative, Informative, and De-Amplifying: Requirements for Robust Bayesian Active Learning under Model Misspecificationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Efficient Adaptive Data Acquisition via Pretrained Belief Representationscited by 2
  2. 2026Certifying Interventional Agreement Among Observationally Equivalent Causal Modelscited by 0