mlsanityData to 7 Oct 2026

Neural Approximate Sufficient Statistics for Implicit Models

arXiv 2010.10079 ↗First posted 20 Oct 2020stat.ML cs.AI cs.LGcited by 72

Not on the map. Why?

Abstract (arXiv)

We consider the fundamental problem of how to automatically construct summary statistics for implicit generative models where the evaluation of the likelihood function is intractable, but sampling data from the model is possible. The idea is to frame the task of constructing sufficient statistics as learning mutual information maximizing representations of the data with the help of deep neural networks. The infomax learning procedure does not need to estimate any density or density ratio. We apply our approach to both traditional approximate Bayesian computation and recent neural likelihood methods, boosting their performance on a range of tasks.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 13; 2023: 13; 2024: 10; 2025: 17; 2026: 8.

72 papers.

Sort:

  1. 2021Benchmarking Simulation-Based Inferencecited by 160
  2. 2021Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoodscited by 61
  3. 2023Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationcited by 57
  4. 2023Learning Robust Statistics for Simulation-based Inference under Model Misspecificationcited by 48
  5. 2022Robust Neural Posterior Estimation and Statistical Model Criticismcited by 45
  6. 2023Sampling-Based Accuracy Testing of Posterior Estimators for General Inferencecited by 45
  7. 2022Variational methods for simulation-based inferencecited by 43
  8. 2023JANA: Jointly Amortized Neural Approximation of Complex Bayesian Modelscited by 41
  9. 2024Neural Methods for Amortized Inferencecited by 36
  10. 2022Predictive Inference with Feature Conformal Predictioncited by 33
  11. 2025Simulation-Based Inference: A Practical Guidecited by 30
  12. 2021Gradient-based Bayesian Experimental Design for Implicit Models using Mutual Information Lower Boundscited by 26
38 more
  1. 2024Addressing Misspecification in Simulation-based Inference through Data-driven Calibrationcited by 26
  2. 2023Sensitivity-Aware Amortized Bayesian Inferencecited by 20
  3. 2021Learning Prototype-oriented Set Representations for Meta-Learningcited by 19
  4. 2021Group equivariant neural posterior estimationcited by 16
  5. 2022Black-box Bayesian inference for economic agent-based modelscited by 13
  6. 2023Neural Bayes Estimators for Irregular Spatial Data using Graph Neural Networkscited by 13
  7. 2025Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Modelscited by 13
  8. 2024Amortized Bayesian Multilevel Modelscited by 12
  9. 2021Unifying Likelihood-free Inference with Black-box Optimization and Beyondcited by 10
  10. 2025Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluationcited by 10
  11. 2022Learning Summary Statistics for Bayesian Inference with Autoencoderscited by 9
  12. 2022Approximate Bayesian Computation with Domain Expert in the Loopcited by 9
  13. 2024Poly-View Contrastive Learningcited by 9
  14. 2025Simulation-based Bayesian inference under model misspecificationcited by 9
  15. 2021TIP: Task-Informed Motion Prediction for Intelligent Vehiclescited by 8
  16. 2022Amortised Likelihood-free Inference for Expensive Time-series Simulators with Signatured Ratio Estimationcited by 8
  17. 2023Scalable Infomin Learningcited by 8
  18. 2023Simulation-based Inference for High-dimensional Data using Surjective Sequential Neural Likelihood Estimationcited by 8
  19. 2024Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks: An Extended Investigationcited by 8
  20. 2024Compositional simulation-based inference for time seriescited by 8
  21. 2021A Generalizable Model-and-Data Driven Approach for Open-Set RFF Authenticationcited by 7
  22. 2022Statistical applications of contrastive learningcited by 5
  23. 2022Efficient identification of informative features in simulation-based inferencecited by 5
  24. 2022Embed and Emulate: Learning to estimate parameters of dynamical systems with uncertainty quantificationcited by 5
  25. 2024Simulation-based Inference with the Python Package sbijaxcited by 5
  26. 2025Robust Simulation-Based Inference under Missing Data via Neural Processescited by 5
  27. 2021Robust and integrative Bayesian neural networks for likelihood-free parameter inferencecited by 4
  28. 2021Bayesian Optimal Experimental Design for Simulator Models of Cognitioncited by 4
  29. 2025Inductive Domain Transfer In Misspecified Simulation-Based Inferencecited by 4
  30. 2025Neural Mutual Information Estimation with Vector Copulascited by 4
  31. 2023Designing Optimal Behavioral Experiments Using Machine Learningcited by 3
  32. 2023Fuse It or Lose It: Deep Fusion for Multimodal Simulation-Based Inferencecited by 3
  33. 2024Hybrid Summary Statisticscited by 3
  34. 2025Amortized Bayesian Mixture Modelscited by 3
  35. 2025Posterior SBC: Simulation-Based Calibration Checking Conditional on Datacited by 3
  36. 2025Generative Distribution Embeddings: Lifting autoencoders to the space of distributions for multiscale representation learningcited by 3
  37. 2026Minimum Distance Summaries for Robust Neural Posterior Estimationcited by 3
  38. 2023Exploiting Inferential Structure in Neural Processescited by 2

50 most cited of 72 All 72 (JSON)