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

94 papers6 papers in the last four weeks, down 71% on the four weeks before. 0.0% of all new papers.

  1. ACTIVA: Amortized Causal Effect Estimation via Variational Autoencoders

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

  2. Adaptive teachers for amortized samplers

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

  3. Amortizing intractable inference in large language models

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

  4. 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