mlsanityData to 14 Oct 2026

JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference

arXiv 2512.22999 ↗First posted 28 Dec 2025stat.ML cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We consider problems of parameter estimation where design variables can be actively optimized to maximize information gain. To this end, we introduce JADAI, a framework that jointly amortizes Bayesian adaptive design and inference by training a policy, a history network, and an inference network end-to-end. The networks minimize a generic loss that aggregates incremental reductions in posterior error along experimental sequences. Inference networks are instantiated with diffusion-based posterior estimators that can approximate high-dimensional and multimodal posteriors at every experimental step. Across standard adaptive design benchmarks, JADAI achieves superior or competitive performance.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 46 of its 79 references that are in the map. First posted on arXiv 28 Dec 2025.

Builds on

46 of 79 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2022Flow Matching for Generative Modelingcited by 5,702
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  8. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  9. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  10. 2015Variational Inference with Normalizing Flowscited by 2,170
  11. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  12. 2019The frontier of simulation-based inferencecited by 502
34 more
  1. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 422
  2. 2023Understanding Diffusion Objectives as the ELBO with Simple Data Augmentationcited by 304
  3. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 242
  4. 2020BayesFlow: Learning complex stochastic models with invertible neural networkscited by 144
  5. 2023Modern Bayesian Experimental Designcited by 125
  6. 2019Variational Bayesian Optimal Experimental Designcited by 116
  7. 2021Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Designcited by 106
  8. 2023Flow Matching for Scalable Simulation-Based Inferencecited by 101
  9. 2022Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matchingcited by 80
  10. 2020Neural Approximate Sufficient Statistics for Implicit Modelscited by 74
  11. 2021Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoodscited by 61
  12. 2019A Unified Stochastic Gradient Approach to Designing Bayesian-Optimal Experimentscited by 58
  13. 2020Bayesian Experimental Design for Implicit Models by Mutual Information Neural Estimationcited by 56
  14. 2022Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Modelscited by 50
  15. 2022Optimizing Sequential Experimental Design with Deep Reinforcement Learningcited by 46
  16. 2024Neural Methods for Amortized Inferencecited by 39
  17. 2025Simulation-Based Inference: A Practical Guidecited by 32
  18. 2024Amortized Probabilistic Conditioning for Optimization, Simulation and Inferencecited by 23
  19. 2023Consistency Models for Scalable and Fast Simulation-Based Inferencecited by 22
  20. 2024Amortized Bayesian Experimental Design for Decision-Makingcited by 21
  21. 2019Optimal experimental design via Bayesian optimization: active causal structure learning for Gaussian process networkscited by 18
  22. 2020OutbreakFlow: Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks and its application to the COVID-19 pandemics in Germanycited by 18
  23. 2022Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Modelscited by 16
  24. 2024Variational Bayesian Optimal Experimental Design with Normalizing Flowscited by 13
  25. 2025Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Designcited by 12
  26. 2024Bayesian Experimental Design via Contrastive Diffusionscited by 11
  27. 2025Diffusion Models in Simulation-Based Inference: A Tutorial Reviewcited by 11
  28. 2024Probabilistic Bayesian optimal experimental design using conditional normalizing flowscited by 10
  29. 2023Variational Sequential Optimal Experimental Design using Reinforcement Learningcited by 8
  30. 2025ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisitioncited by 8
  31. 2024Conditional diffusions for amortized neural posterior estimationcited by 7
  32. 2023Statistically Efficient Bayesian Sequential Experiment Design via Reinforcement Learning with Cross-Entropy Estimatorscited by 6
  33. 2025Optimizing Likelihoods via Mutual Information: Bridging Simulation-Based Inference and Bayesian Optimal Experimental Designcited by 2
  34. 2019A comprehensive evaluation of full-reference image quality assessment algorithms on KADID-10kcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Action-BED: Task-Driven Bayesian Experimental Design with Singly Intractable Objectivescited by 2
  2. 2026Efficient Adaptive Data Acquisition via Pretrained Belief Representationscited by 2
  3. 2026Overcoming Selection Bias in Statistical Studies With Amortized Bayesian Inferencecited by 0
  4. 2026Deep adaptive design with an evidential bias criterioncited by 0