A point cloud approach to generative modeling for galaxy surveys at the field level

Carolina Cuesta-Lazaro, Siddharth Mishra-Sharma
11/28/2023
astro-ph.COastro-ph.IMcs.LG

Official code: smsharma/point-cloud-galaxy-diffusion (25 stars, MIT, JAX, last commit 2024-01-03).

Abstract

We introduce a diffusion-based generative model to describe the distribution of galaxies in our Universe directly as a collection of points in 3-D space (coordinates) optionally with associated attributes (e.g., velocities and masses), without resorting to binning or voxelization. The custom diffusion model can be used both for emulation, reproducing essential summary statistics of the galaxy distribution, as well as inference, by computing the conditional likelihood of a galaxy field. We demonstrate a first application to massive dark matter haloes in the Quijote simulation suite. This approach can be extended to enable a comprehensive analysis of cosmological data, circumventing limitations inherent to summary statistic -- as well as neural simulation-based inference methods.

View on arXivView PDF

Code Implementations(1)

smsharma/point-cloud-galaxy-diffusionOfficial
JAXMIT

Transformer-guided diffusion for galaxy clustering. Code repository associated with https://arxiv.org/abs/2311.17141

255Shell, PythonJan 9, 20232 years agoMIT
dark-matterdiffusiondiffusion-modelsgenerative-modelgnn+6 more

Similar Papers

Reconstructing Galaxy Cluster Mass Maps using Score-based Generative Modeling

86% match2024

Using Galaxy Evolution as Source of Physics-Based Ground Truth for Generative Models

85% match1 repo12024

Category-based Galaxy Image Generation via Diffusion Models

85% match2025

Diffusion-HMC: Parameter Inference with Diffusion-model-driven Hamiltonian Monte Carlo

85% match1 repo82024

Galactification: painting galaxies onto dark matter only simulations using a transformer-based model

84% match2025

How DREAMS are made: Emulating Satellite Galaxy and Subhalo Populations with Diffusion Models and Point Clouds

84% match1 repo92024

Cite this paper

@article{cuestalazaro2023point,
  title  = {A point cloud approach to generative modeling for galaxy surveys at the field level},
  author = {Carolina Cuesta-Lazaro and Siddharth Mishra-Sharma},
  year   = {2023},
  eprint = {2311.17141},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.17141v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.17141.svg)](https://codeofpaper.com/paper/2311.17141)

Discussion