arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.12190cs.LGmath.DS
收藏

神经网络微分方程求解器的局部误差量化

Local error quantification for Neural Network Differential Equation solvers

John A. Paulson School of Engineering and Applied Sciences, Harvard University(哈佛大学约翰·A·保尔森工程与应用科学学院);University of California, Santa Barbara(加州大学圣巴巴拉分校)

Akshunna S. Dogra, William T Redman

摘要:

神经网络已被确定为研究复杂系统的强大工具。一个值得注意的例子是神经网络微分方程(NN DE)求解器,它可以为各种微分方程的解提供函数近似。这样的求解器产生鲁棒的函数表达式,非常适合对感兴趣的量进行进一步的操作(例如,求导),并且能够利用并行化和计算能力的现代进步。然而,缺乏精确的误差量化在预测中的作用:通常,重点是模糊的和/或全局的性能指标,如损失函数和/或获得与预测相关的误差的全局范围。如果没有外部手段或对真实解的完全了解,精确的局部误差量化几乎是不可能的。我们在动态系统NN DE求解器的背景下解决这些问题,利用NN DE求解器中的学习信息来开发方法,使它们更准确和有效,同时仍然追求不依赖外部工具或数据的无监督方法。我们通过可以精确估计NN DE求解器逐点预测误差的方法来实现这一点,从而使用户能够进行有效和有针对性的错误校正。我们通过在一个非线性系统和一个混沌系统上测试我们的方法来验证它们的实用性。

英文摘要:

Neural networks have been identified as powerful tools for the study of complex systems. A noteworthy example is the neural network differential equation (NN DE) solver, which can provide functional approximations to the solutions of a wide variety of differential equations. Such solvers produce robust functional expressions, are well suited for further manipulations on the quantities of interest (for example, taking derivatives), and capable of leveraging the modern advances in parallelization and computing power. However, there is a lack of work on the role precise error quantification can play in their predictions: usually, the focus is on ambiguous and/or global measures of performance like the loss function and/or obtaining global bounds on the errors associated with the predictions. Precise, local error quantification is seldom possible without external means or outright knowledge of the true solution. We address these concerns in the context of dynamical system NN DE solvers, leveraging learnt information within the NN DE solvers to develop methods that allow them to be more accurate and efficient, while still pursuing an unsupervised approach that does not rely on external tools or data. We achieve this via methods that can precisely estimate NN DE solver prediction errors point-wise, thus allowing the user the capacity for efficient and targeted error correction. We exemplify the utility of our methods by testing them on a nonlinear and a chaotic system each.

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。

↑