31 August 2026 to 4 September 2026
University of Malta
Europe/Malta timezone

How do generative diffusion models learn cosmic web environments?

4 Sept 2026, 09:00
20m
Aula Prima (University of Malta)

Aula Prima

University of Malta

Valletta Campus, St Paul Street Valletta VLT 1216, Malta

Speaker

Mehdi Noor

Description

In recent years, generative diffusion models have made rapid progress in learning complex data distributions. In cosmology, they have shown promising results in emulating simulations across diverse cosmological settings, mitigating their computational cost while capturing not only two-point statistics but also higher-order correlations. In this work, we construct an optimised generative diffusion model to emulate the cosmic web (CW), comprising voids, walls, filaments and nodes, which encodes key information about cosmological parameters and the evolution of the large-scale structure in the Universe. In particular, we investigate how diffusion models capture the statistical properties of the CW via self-attention maps by evaluating how well they reproduce distinct CW environments. Based on several statistical estimators, our analysis provides a quantitative assessment of the performance of diffusion models. We further explore how latent generative models learn high-resolution 3D simulation by evaluating the robustness of this approach in preserving CW statistics.

Presentation materials

There are no materials yet.