mlsanityData to 7 Oct 2026

Cosmological Field Emulation and Parameter Inference with Diffusion Models

arXiv 2312.07534 ↗First posted 12 Dec 2023astro-ph.CO astro-ph.IM cs.LGcited by 3

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Cosmological simulations play a crucial role in elucidating the effect of physical parameters on the statistics of fields and on constraining parameters given information on density fields. We leverage diffusion generative models to address two tasks of importance to cosmology -- as an emulator for cold dark matter density fields conditional on input cosmological parameters Omegam and σ8, and as a parameter inference model that can return constraints on the cosmological parameters of an input field. We show that the model is able to generate fields with power spectra that are consistent with those of the simulated target distribution, and capture the subtle effect of each parameter on modulations in the power spectrum. We additionally explore their utility as parameter inference models and find that we can obtain tight constraints on cosmological parameters.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 12 of its 20 references that are in the map. First posted on arXiv 12 Dec 2023.

Builds on

12 of 20 references.

References · 12

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2016Wide Residual Networkscited by 3,057
  6. 2018Group Normalizationcited by 1,514
  7. 2018Efficient Attention: Attention with Linear Complexitiescited by 366
  8. 2015A note on the evaluation of generative modelscited by 291
  9. 2021The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligencecited by 18
  10. 2017CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networkscited by 17
  11. 2021Multifield Cosmology with Artificial Intelligencecited by 12
  12. 2023Multiscale Flow for Robust and Optimal Cosmological Analysiscited by 10

Built on by

Cited by year (2026 to 7 Oct)

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

3 papers.

  1. 2025Conditional Diffusion-Flow models for generating 3D cosmic density fields: applications to f(R) cosmologiescited by 2
  2. 2026Diffusion models recover accurate mixture weights despite score function insensitivitycited by 2
  3. 2026Generative Diffusion Priors for 3D Mapping of the Dark Universecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion-HMC: Parameter Inference with Diffusion-model-driven Hamiltonian Monte Carlo
  2. 2026Cosmo-FOLD: Fast generation and upscaling of field-level cosmological maps with overlap latent diffusion
  3. 2023A point cloud approach to generative modeling for galaxy surveys at the field level
  4. 2022Can denoising diffusion probabilistic models generate realistic astrophysical fields?
  5. 2023Probabilistic reconstruction of Dark Matter fields from biased tracers using diffusion models
  6. 2024Using Galaxy Evolution as Source of Physics-Based Ground Truth for Generative Models
  7. 2023Unified framework for diffusion generative models in SO(3): applications in computer vision and astrophysics
  8. 2023Removing Dust from CMB Observations with Diffusion Models