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 2207.06339math.NAcs.LGcs.NA
收藏

学习自适应网格细化的鲁棒标记策略

Learning robust marking policies for adaptive mesh refinement

Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室);Brown University(布朗大学)

Andrew Gillette, Brendan Keith, Socratis Petrides

AI总结:

本文将自适应网格细化重构为马尔可夫决策过程,利用强化学习在线优化标记策略,避免离线调参,并在泊松方程上验证其鲁棒性和跨域泛化能力。

摘要:

在这项工作中,我们重新审视了标准自适应有限元方法(AFEM)中的标记决策。经验表明,朴素的标记策略会导致自适应网格细化(AMR)中计算资源的低效使用。因此,在实际中使用AFEM通常涉及临时或耗时的离线参数调整,以为标记子程序设置适当的参数。为了解决这些实际问题,我们将AMR重新构建为马尔可夫决策过程,其中细化参数可以在运行时即时选择,无需专家用户预先调整。在这种新范式中,细化参数也通过标记策略自适应选择,该策略可以使用强化学习方法进行优化。我们使用泊松方程在$h$-和$hp$-细化基准问题上演示我们的技术,我们的实验表明,对于许多经典AFEM应用,优越的标记策略仍未被发现。此外,这项工作的一个意外观察是,在一个PDE族上训练的标记策略有时足够鲁棒,能在远离训练族的问题上表现良好。为了说明,我们展示了一个仅在具有单个凹角的2D域上训练的简单$hp$-细化策略,可以部署在更复杂的2D域甚至3D域上,而不会显著损失性能。为了复现和更广泛的采用,我们随此工作提供了我们方法的开源实现。

英文摘要:

In this work, we revisit the marking decisions made in the standard adaptive finite element method (AFEM). Experience shows that a naïve marking policy leads to inefficient use of computational resources for adaptive mesh refinement (AMR). Consequently, using AFEM in practice often involves ad-hoc or time-consuming offline parameter tuning to set appropriate parameters for the marking subroutine. To address these practical concerns, we recast AMR as a Markov decision process in which refinement parameters can be selected on-the-fly at run time, without the need for pre-tuning by expert users. In this new paradigm, the refinement parameters are also chosen adaptively via a marking policy that can be optimized using methods from reinforcement learning. We use the Poisson equation to demonstrate our techniques on $h$- and $hp$-refinement benchmark problems, and our experiments suggest that superior marking policies remain undiscovered for many classical AFEM applications. Furthermore, an unexpected observation from this work is that marking policies trained on one family of PDEs are sometimes robust enough to perform well on problems far outside the training family. For illustration, we show that a simple $hp$-refinement policy trained on 2D domains with only a single re-entrant corner can be deployed on far more complicated 2D domains, and even 3D domains, without significant performance loss. For reproduction and broader adoption, we accompany this work with an open-source implementation of our methods.

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。

↑