arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.12790cs.LGphysics.comp-ph
收藏

具有ODE积分器的Hamilton图网络

Hamiltonian Graph Networks with ODE Integrators

DeepMind(深度思维);NYU(纽约大学)

Alvaro Sanchez-Gonzalez, Victor Bapst, Kyle Cranmer, Peter Battaglia

摘要:

我们介绍了一种方法,在学习模拟模型中施加物理信息的归纳偏见。我们结合图形网络与可微常微分方程积分器作为预测未来状态的机制,和作为内部表示的哈密顿量。我们发现,我们的方法在预测准确性,能量准确性和zero-shot泛化到时间步长和积分器阶数方面优于没有这些偏差的基线。这推进了学习模拟的最新技术,并且原则上适用于物理领域之外。

英文摘要:

We introduce an approach for imposing physically informed inductive biases in learned simulation models. We combine graph networks with a differentiable ordinary differential equation integrator as a mechanism for predicting future states, and a Hamiltonian as an internal representation. We find that our approach outperforms baselines without these biases in terms of predictive accuracy, energy accuracy, and zero-shot generalization to time-step sizes and integrator orders not experienced during training. This advances the state-of-the-art of learned simulation, and in principle is applicable beyond physical domains.

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。

↑