Learning the Universe:利用不可微结构形成模型学习优化宇宙初始条件
Learning the Universe: Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
AI总结:
针对宇宙场级推断中物理模型不可微、难以用梯度法优化的问题,提出无梯度框架LULO,用神经优化器迭代结合完整物理模拟重构宇宙初始条件,在多项宇宙学统计量上实现准确恢复。
摘要:
要充分利用下一代星系成团巡天的观测数据,需要攻克复杂非线性建模中的诸多难题,才能提取小宇宙尺度上蕴含的大量信息。场级推断为利用星系分布的全部信息提供了超越汇总统计量的独特机遇。但当前要解决这些挑战往往需要采用包含不可微组件的数值建模方法,这阻碍了高效的基于梯度的推断方法的应用。本文提出了Learning to Optimize驱动的Learning the Universe(LULO,即学习优化以认知宇宙)框架,这是一种用于重构三维宇宙初始条件的无梯度框架。该方法推进了深度学习技术,训练出一种优化算法,能够在场级层面将最先进的不可微模拟器与观测数据进行拟合。关键在于,该神经优化器仅在迭代流程中充当搜索引擎,始终将完整物理模拟纳入迭代循环,保证了方法的可扩展性与可靠性。我们通过一项实验验证了该方法:从仅含暗物质的N体模拟中、通过球过密度算法识别出的$M_{200\rm{c}}$晕出发,准确重构出了初始条件。重构得到的暗物质和晕过密度场,在非线性区间$k \sim 1h \mathrm{Mpc}^{-1}$的尺度上,与真实值的互相关系数不低于80%。额外的宇宙学测试显示,该方法能准确恢复功率谱、双谱、晕质量函数和速度场。通过这项工作,我们为非线性场级推断展示了一条颇具前景的新路径,该方法不再要求物理模型具备可微性。
英文摘要:
Making the most of next-generation galaxy clustering surveys requires overcoming challenges in complex, non-linear modelling to access the significant amount of information at smaller cosmological scales. Field-level inference has provided a unique opportunity beyond summary statistics to use all of the information of the galaxy distribution. However, addressing current challenges often necessitates numerical modelling that incorporates non-differentiable components, hindering the use of efficient gradient-based inference methods. In this paper, we introduce Learning the Universe by Learning to Optimize (LULO), a gradient-free framework for reconstructing the 3D cosmic initial conditions. Our approach advances deep learning to train an optimization algorithm capable of fitting state-of-the-art non-differentiable simulators to data at the field level. Importantly, the neural optimizer solely acts as a search engine in an iterative scheme, always maintaining full physics simulations in the loop, ensuring scalability and reliability. We demonstrate the method by accurately reconstructing initial conditions from $M_{200\mathrm{c}}$ halos identified in a dark matter-only $N$-body simulation with a spherical overdensity algorithm. The derived dark matter and halo overdensity fields exhibit $\geq80\%$ cross-correlation with the ground truth into the non-linear regime $k \sim 1h$ Mpc$^{-1}$. Additional cosmological tests reveal accurate recovery of the power spectra, bispectra, halo mass function, and velocities. With this work, we demonstrate a promising path forward to non-linear field-level inference surpassing the requirement of a differentiable physics model.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。