arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.16038cond-mat.dis-nncond-mat.stat-mechcond-mat.str-elhep-lathep-th
收藏

用于求解格点上泛函重整化群的物理信息神经网络

Physics-informed neural networks for solving functional renormalization group on a lattice

Takeru Yokota

AI总结:

本文提出利用物理信息神经网络求解格点上泛函重整化群中的高维偏微分方程,并在零维O(N)模型中成功构造了高达N=100维的有效作用量,展示了该方法在缺乏小参数情况下的有效性。

摘要:

在泛函重整化群框架下,求解高维偏微分方程以推导有效作用量是一项艰巨任务,尤其是当需要考虑包括非均匀态在内的各种场构型时,即使在格点上也是如此。我们利用物理信息神经网络(PINNs)作为一种最先进的机器学习方法来求解高维偏微分方程,以克服这一挑战。在零维O(N)模型中,我们数值演示了在N维构型空间上有效作用量的构造,并将N扩展到100。我们的结果强调了PINN近似的有效性,即使在缺乏小参数(如小耦合)的情况下也是如此。

英文摘要:

Addressing high-dimensional partial differential equations to derive effective actions within the functional renormalization group is formidable, especially when considering various field configurations, including inhomogeneous states, even on lattices. We leverage physics-informed neural networks (PINNs) as a state-of-the-art machine learning method for solving high-dimensional partial differential equations to overcome this challenge. In a zero-dimensional O($N$) model, we numerically demonstrate the construction of an effective action on an $N$-dimensional configuration space, extending up to $N=100$. Our results underscore the effectiveness of PINN approximation, even in scenarios lacking small parameters such as a small coupling.

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。

↑