发表机构
Université Paris-Saclay; CNRS; Institut d’Astrophysique Spatiale; Centre national d’études spatiales (CNES); Laboratoire de Physique de l’École normale supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université Paris Cité; Escuela Técnica Superior de Ingenieros Industriales, Universidad Politécnica de Madrid; GISC - Grupo Interdisciplinar de Sistemas Complejos（巴黎萨克雷大学; 法国国家科学研究中心; 空间天体物理研究所; 法国国家太空研究中心; 巴黎高等师范学院物理实验室，ENS，巴黎文理研究大学，CNRS，索邦大学，巴黎西岱大学; 马德里理工大学工业工程师高等学院; 复杂系统跨学科小组）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究在Quijote模拟上训练扩散模型，通过分析自注意力图与T-Web宇宙网环境的对应关系，发现模型在多尺度上捕捉宇宙网结构并编码非高斯信息。
AI 中文摘要
宇宙网由空洞、墙、丝状结构和节点组成的复杂网络构成，编码了结构形成及支配其的宇宙学参数的关键信息。在高精度宇宙学时代，分析下一代星系巡天需要大量数值模拟集合，这促使人们使用生成模型来规避其高昂的计算成本。尽管生成模型在模拟高保真宇宙网方面展现出潜力，但它们捕捉不同宇宙网环境的能力在很大程度上仍未得到探索。在本研究中，我们在Quijote N体模拟套件上训练了一个扩散模型，以研究其自注意力图所学习的语义信息。利用Dice系数和交叉功率谱等统计估计量，我们量化了注意力图与由T-Web分类器定义的宇宙网环境之间的对应关系。我们发现，不同层中不同空间分辨率的注意力图以不同方式捕捉过密和欠密结构，与整体物质分布及各个宇宙网环境均表现出强烈的正相关和反相关。此外，扩散模型主要在中等至大空间尺度上编码宇宙学信息，表明注意力图主要捕捉全局相干结构。我们的结果表明，除了准确再现两点统计量外，扩散模型通过自注意力学习了宇宙网的多尺度表示，包括非高斯信息。
英文摘要
The cosmic web, consisting of an intricate network of voids, walls, filaments, and nodes, encodes key information about structure formation and the cosmological parameters that govern it. In the era of high-precision cosmology, large ensembles of numerical simulations are required to analyse next-generation galaxy surveys, motivating the use of generative models to circumvent their high computational cost. While they have shown promise in emulating high-fidelity cosmic web simulations, their ability to capture distinct cosmic web environments remains largely unexplored. For this study, we trained a diffusion model on the Quijote N-body simulation suite to investigate the semantic information learnt by its self-attention maps. Using statistical estimators such as the Dice coefficient and cross-power spectra, we quantified the correspondence between attention maps and cosmic web environments defined by the T-Web classifier. We find that attention maps of varying spatial resolutions across different layers capture overdense and underdense structures in distinct ways, exhibiting strong positive correlations and anti-correlations with both the overall matter distribution and individual cosmic web environments. Moreover, the diffusion model predominantly encodes cosmological information at intermediate-to-large spatial scales, indicating that attention maps primarily capture globally coherent structures. Our results show that, beyond accurately reproducing two-point statistics, diffusion models learn a multi-scale representation of the cosmic web through self-attention, including non-Gaussian information.
Comments11 pages, 8 figures. Accepted for publication in Astronomy & Astrophysics. Article reference: aa60142-26
