mlsanityData to 14 Oct 2026

Domain-Adaptive Neural Posterior Estimation for Strong Gravitational Lens Analysis

arXiv 2410.16347 ↗First posted 21 Oct 2024astro-ph.IM astro-ph.CO astro-ph.GAcited by 7

Not on the map. Why?

Abstract (arXiv)

Modeling strong gravitational lenses is prohibitively expensive for modern and next-generation cosmic survey data. Neural posterior estimation (NPE), a simulation-based inference (SBI) approach, has been studied as an avenue for efficient analysis of strong lensing data. However, NPE has not been demonstrated to perform well on out-of-domain target data -- e.g., when trained on simulated data and then applied to real, observational data. In this work, we perform the first study of the efficacy of NPE in combination with unsupervised domain adaptation (UDA). The source domain is noiseless, and the target domain has noise mimicking modern cosmology surveys. We find that combining UDA and NPE improves the accuracy of the inference by 1-2 orders of magnitude and significantly improves the posterior coverage over an NPE model without UDA. We anticipate that this combination of approaches will help enable future applications of NPE models to real observational data.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 34 of its 106 references that are in the map. First posted on arXiv 21 Oct 2024.

Builds on

34 of 106 references.

References · 34

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  3. 2019A Comprehensive Survey on Transfer Learningcited by 1,160
  4. 2017Masked Autoregressive Flow for Density Estimationcited by 684
  5. 2019The frontier of simulation-based inferencecited by 502
  6. 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
  7. 2020A Brief Review of Domain Adaptationcited by 288
  8. 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 219
  9. 2019A review of domain adaptation without target labelscited by 156
  10. 2018An introduction to domain adaptation and transfer learningcited by 112
  11. 2020A Review of Single-Source Deep Unsupervised Visual Domain Adaptationcited by 96
  12. 2024All-in-one simulation-based inferencecited by 74
22 more
  1. 2019Transfer Adaptation Learning: A Decade Surveycited by 52
  2. 2021Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networkscited by 49
  3. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 47
  4. 2022Robust Neural Posterior Estimation and Statistical Model Criticismcited by 46
  5. 2022Investigating the Impact of Model Misspecification in Neural Simulation-based Inferencecited by 45
  6. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  7. 2019A Closer Look at Domain Shift for Deep Learning in Histopathologycited by 25
  8. 2020Adversarial Weighting for Domain Adaptation in Regressioncited by 19
  9. 2022Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Surveycited by 12
  10. 2021DeepMerge II: Building Robust Deep Learning Algorithms for Merging Galaxy Identification Across Domainscited by 11
  11. 2022Neural Posterior Estimation with Differentiable Simulatorscited by 9
  12. 2021Unsupervised Domain Adaptation for Constraining Star Formation Historiescited by 8
  13. 2020Domain adaptation techniques for improved cross-domain study of galaxy mergerscited by 7
  14. 2022Accelerated Bayesian SED Modeling using Amortized Neural Posterior Estimationcited by 7
  15. 2023Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Setscited by 6
  16. 2024Preconditioned Neural Posterior Estimation for Likelihood-free Inferencecited by 6
  17. 2021Robustness of deep learning algorithms in astronomy -- galaxy morphology studiescited by 4
  18. 2023Domain Adaptation via Minimax Entropy for Real/Bogus Classification of Astronomical Alertscited by 3
  19. 2023Deep into The Domain Shift: Transfer Learning through Dependence Regularizationcited by 2
  20. 2023nbi: the Astronomer's Package for Neural Posterior Estimationcited by 2
  21. 2024Measuring Domain Shifts using Deep Learning Remote Photoplethysmography Model Similaritycited by 2
  22. 2022Neural Inference of Gaussian Processes for Time Series Data of Quasarscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 2.

7 papers.

  1. 2025Diffusion Models in Simulation-Based Inference: A Tutorial Reviewcited by 11
  2. 2025Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluationcited by 10
  3. 2024Tests for model misspecification in simulation-based inference: from local distortions to global model checkscited by 4
  4. 2025Inductive Domain Transfer In Misspecified Simulation-Based Inferencecited by 4
  5. 2025Misspecification-robust amortised simulation-based inference using variational methodscited by 0
  6. 2026Safe Domain Adaptation for Physics: Overcoming Nuisances, Label Shifts, and Simulation Priorscited by 0
  7. 2026Mitigating Representation Gaps in Amortized Bayesian Inference with Auxiliary Supervisioncited by 0