mlsanityData to 14 Oct 2026

Posterior samples of source galaxies in strong gravitational lenses with score-based priors

arXiv 2211.03812 ↗First posted 7 Nov 2022astro-ph.IM cs.CV cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

Inferring accurate posteriors for high-dimensional representations of the brightness of gravitationally-lensed sources is a major challenge, in part due to the difficulties of accurately quantifying the priors. Here, we report the use of a score-based model to encode the prior for the inference of undistorted images of background galaxies. This model is trained on a set of high-resolution images of undistorted galaxies. By adding the likelihood score to the prior score and using a reverse-time stochastic differential equation solver, we obtain samples from the posterior. Our method produces independent posterior samples and models the data almost down to the noise level. We show how the balance between the likelihood and the prior meet our expectations in an experiment with out-of-distribution data.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 14 of its 49 references that are in the map. First posted on arXiv 7 Nov 2022.

Builds on

14 of 49 references.

References · 14

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  7. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  8. 2022Diffusion models as plug-and-play priorscited by 231
  9. 2013Deep Generative Stochastic Networks Trainable by Backpropcited by 36
  10. 2017Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Netcited by 30
  11. 2021Realistic galaxy image simulation via score-based generative modelscited by 24
  12. 2020AR-DAE: Towards Unbiased Neural Entropy Gradient Estimationcited by 19
2 more
  1. 2022Probabilistic Mass Mapping with Neural Score Estimationcited by 17
  2. 2022Strong Lensing Source Reconstruction Using Continuous Neural Fieldscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 5; 2025: 3; 2026: 4.

20 papers.

Sort:

By area:

  1. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imagingcited by 127
  2. 2023Score-based Data Assimilationcited by 96
  3. 2024Amortizing intractable inference in diffusion models for vision, language, and controlcited by 72
  4. 2024Learning Diffusion Priors from Observations by Expectation Maximizationcited by 61
  5. 2024Improved off-policy training of diffusion samplerscited by 48
  6. 2023Sampling-Based Accuracy Testing of Posterior Estimators for General Inferencecited by 46
  7. 2023Variational Bayesian Imaging with an Efficient Surrogate Score-based Priorcited by 17
  8. 2023Improving Gradient-guided Nested Sampling for Posterior Inferencecited by 14
  9. 2024Blind Inversion using Latent Diffusion Priorscited by 10
  10. 2023Diffusion Models for Probabilistic Deconvolution of Galaxy Imagescited by 4
  11. 2023Bayesian Imaging for Radio Interferometry with Score-Based Priorscited by 3
  12. 2023Echoes in the Noise: Posterior Samples of Faint Galaxy Surface Brightness Profiles with Score-Based Likelihoods and Priorscited by 2
8 more
  1. 2025A Malliavin-Gamma calculus approach to Score Based Diffusion Generative models for random fieldscited by 2
  2. 2025Blind Strong Gravitational Lensing Inversion: Joint Inference of Source and Lens Mass with Score-Based Modelscited by 2
  3. 2026Generative Models and Statistical Validationcited by 2
  4. 2024An Unconditional Representation of the Conditional Score in Infinite-Dimensional Linear Inverse Problemscited by 1
  5. 2026MIRA: A Score for Conditional Distribution Accuracy and Model Comparisoncited by 1
  6. 2026ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imagingcited by 1
  7. 2025Solving Bayesian inverse problems with diffusion priors and off-policy RLcited by 0
  8. 2026Variance-Reduced Diffusion Sampling via Target Score Identitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines
  2. 2026Generative Diffusion Priors for 3D Mapping of the Dark Universe
  3. 2025IRIS: A Bayesian Approach for Image Reconstruction in Radio Interferometry with expressive Score-Based priors
  4. 2024Bayesian Deconvolution of Astronomical Images with Diffusion Models: Quantifying Prior-Driven Features in Reconstructions
  5. 2025A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors
  6. 2024Using Galaxy Evolution as Source of Physics-Based Ground Truth for Generative Models
  7. 2025Recent Advances in Simulation-based Inference for Gravitational Wave Data Analysis
  8. 2024Flow Matching for Posterior Inference with Simulator Feedback