mlsanityData to 7 Oct 2026

Amortized Factor Inference Networks for Posterior Inference

arXiv 2605.26419 ↗First posted 26 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Amortized inference promises fast test-time Bayesian inference, but existing methods are inherently tied to fixed models. Extending amortization to unseen models typically requires retraining or costly test-time finetuning. In this paper, we ask: is it possible to build a single inference network capable of generalizing across varying priors, likelihoods, and dimensionality? We introduce Amortized Factor Inference Networks (AFINs), a family of encode-merge-decode inference networks built on dimension-independent modules that map a model specification and its observations to the parameters of a variational posterior. Experimentally, a single trained AFIN achieves posterior accuracy comparable to NUTS and several variational inference methods, while requiring 2 to 4 orders of magnitude less test-time compute. Code is available at https://github.com/joohwanko/AFINs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 26 May 2026.

Builds on

39 of 61 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  3. 2015Variational Inference with Normalizing Flowscited by 2,161
  4. 2016Density estimation using Real NVPcited by 2,029
  5. 2016Variational Inference: A Review for Statisticianscited by 1,466
  6. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  7. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  8. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  9. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
  10. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  11. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  12. 2019Neural Spline Flowscited by 590
27 more
  1. 2019The frontier of simulation-based inferencecited by 490
  2. 2021Transformers Can Do Bayesian Inferencecited by 338
  3. 2013Black Box Variational Inferencecited by 317
  4. 2018Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flowscited by 217
  5. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 216
  6. 2021Benchmarking Simulation-Based Inferencecited by 160
  7. 2020BayesFlow: Learning complex stochastic models with invertible neural networkscited by 139
  8. 2023Flow Matching for Scalable Simulation-Based Inferencecited by 97
  9. 2020On Contrastive Learning for Likelihood-free Inferencecited by 96
  10. 2024All-in-one simulation-based inferencecited by 71
  11. 2022Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Modelscited by 50
  12. 2020Markovian Score Climbing: Variational Inference with KL(p||q)cited by 46
  13. 2022Compositional Score Modeling for Simulation-based Inferencecited by 46
  14. 2023JANA: Jointly Amortized Neural Approximation of Complex Bayesian Modelscited by 41
  15. 2016Inference Compilation and Universal Probabilistic Programmingcited by 31
  16. 2025Can Transformers Learn Full Bayesian Inference in Context?cited by 30
  17. 2021Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergencecited by 29
  18. 2024Amortized Probabilistic Conditioning for Optimization, Simulation and Inferencecited by 22
  19. 2019Meta-Amortized Variational Inference and Learningcited by 21
  20. 2023Sensitivity-Aware Amortized Bayesian Inferencecited by 20
  21. 2025Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Modelscited by 13
  22. 2025Distribution Transformers: Fast Approximate Bayesian Inference With On-The-Fly Prior Adaptationcited by 12
  23. 2022Transport Score Climbing: Variational Inference Using Forward KL and Adaptive Neural Transportcited by 8
  24. 2022Foundation Posteriors for Approximate Probabilistic Inferencecited by 6
  25. 2024Disentangling impact of capacity, objective, batchsize, estimators, and step-size on flow VIcited by 5
  26. 2025Model-Informed Flows for Bayesian Inferencecited by 3
  27. 2022Reconstructing the Universe with Variational self-Boosted Samplingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Improving the Accuracy of Amortized Model Comparison with Self-Consistency
  2. 2023Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference
  3. 2023Adversarial robustness of amortized Bayesian inference
  4. 2025PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inference
  5. 2026Unsupervised Continual Learning for Amortized Bayesian Inference
  6. 2022Amortized backward variational inference in nonlinear state-space models
  7. 2025Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Data
  8. 2026I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning