mlsanityData to 7 Oct 2026

Neural Network Prediction of Strong Lensing Systems with Domain Adaptation and Uncertainty Quantification

arXiv 2411.03334 ↗First posted 23 Oct 2024astro-ph.IM astro-ph.CO astro-ph.GAcited by 2

Not on the map. Why?

Abstract (arXiv)

Modeling strong gravitational lenses is computationally expensive for the complex data from modern and next-generation cosmic surveys. Deep learning has emerged as a promising approach for finding lenses and predicting lensing parameters, such as the Einstein radius. Mean-variance Estimators (MVEs) are a common approach for obtaining aleatoric (data) uncertainties from a neural network prediction. However, neural networks have not been demonstrated to perform well on out-of-domain target data successfully - e.g., when trained on simulated data and applied to real, observational data. In this work, we perform the first study of the efficacy of MVEs in combination with unsupervised domain adaptation (UDA) on strong lensing data. The source domain data is noiseless, and the target domain data has noise mimicking modern cosmology surveys. We find that adding UDA to MVE increases the accuracy on the target data by a factor of about two over an MVE model without UDA. Including UDA also permits much more well-calibrated aleatoric uncertainty predictions. Advancements in this approach may enable future applications of MVE models to real observational data.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 49 of its 123 references that are in the map. First posted on arXiv 23 Oct 2024.

Builds on

49 of 123 references.

References · 49

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  5. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  6. 2021Domain Generalization: A Surveycited by 760
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  8. 2019The frontier of simulation-based inferencecited by 490
  9. 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
  10. 2019Deep Evidential Regressioncited by 354
  11. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
  12. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
37 more
  1. 2020A Brief Review of Domain Adaptationcited by 287
  2. 2021Ensemble deep learning: A reviewcited by 283
  3. 2019A review of domain adaptation without target labelscited by 154
  4. 2016Correlation Alignment for Unsupervised Domain Adaptationcited by 146
  5. 2020Bayesian Neural Networks: An Introduction and Surveycited by 130
  6. 2022On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networkscited by 119
  7. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  8. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
  9. 2019Reliable training and estimation of variance networkscited by 63
  10. 2022Deep Ensembles Work, But Are They Necessary?cited by 63
  11. 2023Domain Adaptation for Time Series Under Feature and Label Shiftscited by 60
  12. 2019Transfer Adaptation Learning: A Decade Surveycited by 52
  13. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 46
  14. 2022The Unreasonable Effectiveness of Deep Evidential Regressioncited by 40
  15. 2021Is MC Dropout Bayesian?cited by 35
  16. 2021AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantificationcited by 31
  17. 2023Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensemblescited by 30
  18. 2023A Primer on Bayesian Neural Networks: Review and Debatescited by 26
  19. 2021Multivariate Deep Evidential Regressioncited by 23
  20. 2020Notes on the Behavior of MC Dropoutcited by 21
  21. 2023Optimal Training of Mean Variance Estimation Neural Networkscited by 17
  22. 2024Uncertainty Regularized Evidential Regressioncited by 13
  23. 2021DeepMerge II: Building Robust Deep Learning Algorithms for Merging Galaxy Identification Across Domainscited by 10
  24. 2021DeepAdversaries: Examining the Robustness of Deep Learning Models for Galaxy Morphology Classificationcited by 10
  25. 2023Better Practices for Domain Adaptationcited by 9
  26. 2021Mining for Strong Gravitational Lenses with Self-supervised Learningcited by 8
  27. 2023DeepAstroUDA: Semi-Supervised Universal Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detectioncited by 8
  28. 2020Domain adaptation techniques for improved cross-domain study of galaxy mergerscited by 7
  29. 2021Bayesian Neural Networks: Essentialscited by 7
  30. 2023Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Setscited by 6
  31. 2024Scaling Laws for Galaxy Imagescited by 5
  32. 2021Robustness of deep learning algorithms in astronomy -- galaxy morphology studiescited by 4
  33. 2022Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detectioncited by 4
  34. 2024DomainVerse: A Benchmark Towards Real-World Distribution Shifts For Tuning-Free Adaptive Domain Generalizationcited by 3
  35. 2023Visualizing Transferred Knowledge: An Interpretive Model of Unsupervised Domain Adaptationcited by 1
  36. 2023Galaxy Classification Using Transfer Learning and Ensemble of CNNs With Multiple Colour Spacescited by 1
  37. 2024A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspectivecited by 1

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification with Equivariant Neural Networkscited by 2
  2. 2025From Simulations to Surveys: Domain Adaptation for Galaxy Observationscited by 0