基于伴随方法的可微宇宙学模拟
Differentiable Cosmological Simulation with Adjoint Method
AI总结:
提出基于伴随方法和反向时间积分的可微宇宙学模拟新方法,突破内存限制,实现更大规模、更精确的场级正向建模,并在开源PM N体库pmwd中实现,基于JAX实现完全可微及GPU高性能。
摘要:
深度学习的快速发展不仅带来了众多强大的神经网络,也带来了惠及既有科学研究的突破。特别是,自动微分(AD)工具和GPU等计算加速器促进了利用可微模拟对宇宙进行正向建模。基于解析或自动反向传播,当前的可微宇宙学模拟受限于内存,因此在时间与空间/质量分辨率之间存在权衡,通常两者都会有所牺牲。我们提出了一种不受此类约束的新方法,采用伴随方法和反向时间积分。它能够在场级别实现更大规模、更精确的正向建模,并将改进基于梯度的优化和推断。我们在开源粒子网格(PM)N体库pmwd(带导数的粒子网格)中实现了该方法。基于强大的AD系统JAX,pmwd是完全可微的,并且在GPU上具有高性能。
英文摘要:
Rapid advances in deep learning have brought not only myriad powerful neural networks, but also breakthroughs that benefit established scientific research. In particular, automatic differentiation (AD) tools and computational accelerators like GPUs have facilitated forward modeling of the Universe with differentiable simulations. Based on analytic or automatic backpropagation, current differentiable cosmological simulations are limited by memory, and thus are subject to a trade-off between time and space/mass resolution, usually sacrificing both. We present a new approach free of such constraints, using the adjoint method and reverse time integration. It enables larger and more accurate forward modeling at the field level, and will improve gradient based optimization and inference. We implement it in an open-source particle-mesh (PM) $N$-body library pmwd (particle-mesh with derivatives). Based on the powerful AD system JAX, pmwd is fully differentiable, and is highly performant on GPUs.
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。