arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1801.09197stat.MLcs.LGcs.SCmath.AC
收藏

数学线性约束高斯过程

Algorithmic Linearly Constrained Gaussian Processes

Ostwestfalen-Lippe University of Applied Sciences(奥斯威斯特法伦-利普应用科学大学);Department of Electrical Engineering and Computer Science(电气工程与计算机科学系);Lemgo(伦戈)

Markus Lange-Hegermann

摘要:

算法上构造了满足线性微分方程的多输出高斯过程先验。我们的方法试图使用Gröbner基地参数化方程的所有解决方案。如果成功,则沿着参数化的前推高斯过程是期望的先验。我们考虑几个例子,从物理学,geomathematics和控制,其中充分非齐次系统的麦克斯韦方程组。通过以一种新的方式将随机学习和计算机代数结合在一起,我们将噪声观测与精确的代数计算相结合。

英文摘要:

We algorithmically construct multi-output Gaussian process priors which satisfy linear differential equations. Our approach attempts to parametrize all solutions of the equations using Gröbner bases. If successful, a push forward Gaussian process along the paramerization is the desired prior. We consider several examples from physics, geomathematics and control, among them the full inhomogeneous system of Maxwell's equations. By bringing together stochastic learning and computer algebra in a novel way, we combine noisy observations with precise algebraic computations.

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。

↑