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 2610.20525cs.LGcs.SYeess.SYnlin.CDstat.AP
收藏

物理即网络:快速、无需训练的神经仿真

The Physics Is the Network: Fast, Training-Free Neural Emulation

University of Michigan(密歇根大学);NASA Goddard Institute for Space Studies(美国宇航局戈达德太空研究所);Massachusetts Institute of Technology(麻省理工学院)

Luka Todorovic, Kaushal Gianchandani, Sai Ravela

AI总结:

该研究提出无需训练的PolyNet模型,将多项式动力学的连续时间神经表示与简单循环网络耦合,在Korteweg-de Vries方程仿真中精度可媲美数值求解器,兼具高GPU吞吐量与良好的集合缩放性能。

摘要:

神经仿真无需学习已知物理的替代模型。我们研究PolyNets,它将多项式动力学的连续时间神经表示与用于离散时间积分的简单循环网络耦合。当控制系数已知时,所得张量图无需训练,可保留规定的数值格式,同时支持高效硬件执行与并行仿真。我们使用一维Korteweg-de Vries方程,将PolyNet与CPU和GPU有限差分Runge-Kutta求解器,以及三种训练过的神经模型(状态映射仿真器、物理信息预测器和学习趋势积分器)进行比较。解析孤子解为不同网格分辨率、10^6个色散缩放时间步、多达10^4条轨迹的集合以及不同初始振幅下的振幅和相位误差提供参考。PolyNet的精度可与数值求解器媲美,包括在超出训练模型训练条件的振幅下,它兼具该保真度与高GPU吞吐量(在测试的分辨率范围内近似恒定)以及良好的集合缩放性能。

英文摘要:

Neural emulation need not require learning a substitute for known physics. We investigate PolyNets that couple a continuous-time neural representation of polynomial dynamics with a simple recurrent network for discrete-time integration. When the governing coefficients are known, the resulting tensor graph requires no training and preserves the prescribed numerical scheme while enabling efficient hardware execution and parallel simulation. Using the one-dimensional Korteweg-de Vries equation, we compare PolyNet with CPU and GPU finite-difference Runge-Kutta solvers and three trained neural models: a state-map emulator, a physics-informed predictor, and a learned-tendency integrator. Analytical soliton solutions provide a reference for amplitude and phase errors across grid resolutions, 10^6 dispersively scaled time steps, ensembles of up to 10^4 trajectories, and varying initial amplitudes. PolyNet achieves accuracy comparable to the numerical solvers, including at amplitudes outside the learned models' training conditions. It combines this fidelity with high GPU throughput, approximately constant over the tested resolution range, and favorable ensemble scaling.

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。

↑