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 2104.03562math.DScs.LG
收藏

使用强化学习实现数值积分的高效时间步进

Efficient time stepping for numerical integration using reinforcement learning

Paderborn University(帕德博恩大学);LMU Munich(慕尼黑大学);Zuse Institute Berlin(柏林祖斯研究所)

Michael Dellnitz, Eyke Hüllermeier, Marvin Lücke, Sina Ober-Blöbaum, Christian Offen, Sebastian Peitz, Karlson Pfannschmidt

AI总结:

本文提出将经典求积规则或 ODE 求解器与强化学习的数据驱动时间步进控制器结合,使数值方法适配特定问题类别,从而在混沌等复杂系统中优于现有自适应方案。

摘要:

科学和工程中的许多问题都需要对积分或微分方程的解进行高效的数值近似。对于动力学快速变化的系统,等距离散化通常并不可取,因为它要么导致难以接受的巨大误差,要么带来过高的计算开销。为此,人们开发了自适应方法,例如基于 Runge–Kutta 对的求解器,它们在每一步根据局部误差估计调整步长。尽管经典方法适用范围很广,并且在规则系统上具有很高的效率,但当结构复杂的系统(如混沌系统)触发低效的步长拒绝机制时,它们可能表现出次优行为。为克服这些问题,我们提出一种使数值方案适配当前问题类别的方法。其实现方式是将简单的经典求积规则或 ODE 求解器与数据驱动的时间步进控制器相结合。与直接学习 ODE 的解算子相比,由于我们的方法采用经典数值方案作为基础方法,因此它能更好地泛化到未见过的初始数据。同时,该方法能够利用已识别出的问题类别结构,因而优于最先进的自适应方案。若干算例展示了其卓越的效率。源代码可在 https://github.com/lueckem/quadrature-ML 获取。

英文摘要:

Many problems in science and engineering require an efficient numerical approximation of integrals or solutions to differential equations. For systems with rapidly changing dynamics, an equidistant discretization is often inadvisable as it either results in prohibitively large errors or computational effort. To this end, adaptive schemes, such as solvers based on Runge--Kutta pairs, have been developed which adapt the step size based on local error estimations at each step. While the classical schemes apply very generally and are highly efficient on regular systems, they can behave sub-optimal when an inefficient step rejection mechanism is triggered by structurally complex systems such as chaotic systems. To overcome these issues, we propose a method to tailor numerical schemes to the problem class at hand. This is achieved by combining simple, classical quadrature rules or ODE solvers with data-driven time-stepping controllers. Compared with learning solution operators to ODEs directly, it generalises better to unseen initial data as our approach employs classical numerical schemes as base methods. At the same time it can make use of identified structures of a problem class and, therefore, outperforms state-of-the-art adaptive schemes. Several examples demonstrate superior efficiency. Source code is available at https://github.com/lueckem/quadrature-ML.

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。

↑