Overview

Amortized inference learns a reusable mapping from observations and model information to posterior estimates, predictions, or samples, shifting computation from each new case to training. Common approaches include simulation-based neural posterior estimation, variational encoders and normalizing flows, structured message passing, and transformer-based prior-fitted or in-context models. These methods are used in settings such as inverse problems, state-space models, survival analysis, and hierarchical statistics, often with MCMC or benchmark posteriors used to assess accuracy and calibration. The central tension is that fast single-pass inference can lose accuracy or uncertainty calibration on rare cases, shifted data, or complex posteriors, motivating test-time refinement and stronger evaluations of generalization.

Latest papers

CardsList

87 papers17 papers in the last four weeks, up 113% on the four weeks before. 0.1% of all new papers.

  1. It Just Takes Two: Scaling Amortized Inference to Large Sets

    May 8, 2026Antoine Wehenkel, Michael Kagan, Lukas Heinrich +1Neural Posterior EstimationRepresentation Learning

  2. One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operators

    May 7, 2026Panos Tsimpos, Edoardo Calvello, Ayoub Belhadji +1Amortized InferenceBayesian Inference

  3. Amortized Variational Inference for Joint Posterior and Predictive Distributions in Bayesian Uncertainty Quantification

    May 5, 2026Nan Feng, Xun HuanUncertainty QuantificationAmortized Inference

  4. Fast Bayesian equipment condition monitoring via simulation based inference: applications to heat exchanger health

    Apr 22, 2026Peter Collett, Alexander Johannes Stasik, Simone Casolo +1Simulation-Based InferenceEfficient Inference

  5. Amortized Vine Copulas for High-Dimensional Density and Information Estimation

    Apr 22, 2026Houman SafaaiCopula ModelsAmortized Inference

  6. Overcoming Selection Bias in Statistical Studies With Amortized Bayesian Inference

    Apr 20, 2026Jonas Arruda, Sophie Chervet, Paula Staudt +6Simulation-Based InferenceAmortized Inference

  7. Amortized Filtering and Smoothing with Conditional Normalizing Flows

    Apr 8, 2026Tiangang Cui, Xiaodong Feng, Chenlong Pei +2Bayesian FilteringData Assimilation

  8. Instance-Adaptive Parametrization for Amortized Variational Inference

    Apr 8, 2026Andrea Pollastro, Andrea Apicella, Francesco Isgrò +1Variational AutoencodersAmortized Inference

  9. Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks

    Mar 31, 2026Dmitrii Seletkov, Paul Hager, Georgios Kaissis +3Survival AnalysisPrior-Data Fitted Networks

  10. Amortized Inference for Correlated Discrete Choice Models via Equivariant Neural Networks

    Mar 25, 2026Easton Huch, Michael KeaneNeural Surrogate ModelingAmortized Inference

  11. Identifiability and amortized inference limitations in Kuramoto models

    Mar 23, 2026Emma Hannula, Jana de Wiljes, Matthew T. Moores +2Kuramoto ModelAmortized Inference

  12. Amortized Variational Inference for Logistic Regression with Missing Covariates

    Mar 22, 2026M. Cherifi, Aude Sportisse, Xujia Zhu +2Learning with Missing DataLogistic Regression

  13. CogFormer: Learn All Your Models Once

    Mar 20, 2026Jerry M. Huang, Lukas Schumacher, Niek Stevenson +1Amortized InferenceSimulation-Based Inference

  14. Sparsely-Supervised Data Assimilation via Physics-Informed Schrödinger Bridge

    Mar 20, 2026Dohyun Bu, Chanho Kim, Seokun Choi +1Data AssimilationPhysics-Informed Generative Modeling

  15. FalconBC: Flow matching for Amortized inference of Latent-CONditioned physiologic Boundary Conditions

    Mar 18, 2026Chloe H. Choi, Alison L. Marsden, Daniele E. SchiavazziAmortized InferenceConditional Flow Matching

  16. Scalable Simulation-Based Model Inference with Test-Time Complexity Control

    Mar 16, 2026Manuel Gloeckler, J. P. Manzano-Patrón, Stamatios N. Sotiropoulos +2Model SelectionSimulation-Based Inference

  17. Unsupervised Continual Learning for Amortized Bayesian Inference

    Feb 26, 2026Aayush Mishra, Šimon Kucharský, Paul-Christian BürknerAmortized InferenceOnline Continual Learning

  18. Amortized Bayesian inference for actigraph time sheet data from mobile devices

    Feb 24, 2026Daniel Zhou, Sudipto BanerjeeAmortized InferenceWearable Health Monitoring

  19. OneFlowSBI: One Model, Many Queries for Simulation-Based Inference

    Jan 30, 2026Mayank Nautiyal, Li Ju, Melker Ernfors +5Simulation-Based InferenceAmortized Inference

  20. Neural Architectures for Amortized Bayesian Inference: Statistical Foundations and Empirical Assessments

    Jan 12, 2026Roy Shivam Ram Shreshtth, Arnab Hazra, Gourab MukherjeeUncertainty QuantificationAmortized Inference

  21. JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference

    Dec 28, 2025Niels Bracher, Lars Kühmichel, Desi R. Ivanova +3Parameter EstimationAmortized Inference

  22. ACTIVA: Amortized Causal Effect Estimation via Variational Autoencoders

    Mar 3, 2025Andreas Sauter, Saber Salehkaleybar, Frank van Harmelen +2Causal Effect EstimationCausal Intervention

  23. Adaptive teachers for amortized samplers

    Oct 2, 2024Minsu Kim, Sanghyeok Choi, Taeyoung Yun +7Amortized InferenceRL Exploration

  24. Amortizing intractable inference in large language models

    Oct 6, 2023Edward J. Hu, Moksh Jain, Eric Elmoznino +4Amortized InferenceLLM Fine-Tuning

  25. Delta-AI: Local objectives for amortized inference in sparse graphical models

    Oct 3, 2023Jean-Pierre Falet, Hae Beom Lee, Esmeralda S. Whitammer +6Amortized InferenceProbabilistic Graphical Models