arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2102.11923math.DScs.LGmath-phmath.MP
收藏

KAM理论与统计学习理论相结合:具有非零训练损失的Hamilton神经网络

KAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-Zero Training Loss

Kobe University(神户大学);Osaka University(大阪大学)

Yuhan Chen, Takashi Matsubara, Takaharu Yaguchi

摘要:

许多物理现象都是由哈密顿力学使用能量函数(哈密顿量)来描述的。近年来,将Hamilton函数近似为神经网络的Hamilton神经网络及其扩展引起了人们的广泛关注。这是一个非常强大的方法,但它在理论研究中的应用仍然有限。结合统计学习理论和Kolmogorov-Arnold-Moser(KAM)理论,对Hamilton神经网络在学习误差不完全为零时的行为进行了理论分析.具有非零误差的Hamilton神经网络可以被认为是来自真实动力学的扰动,并且哈密顿方程的扰动理论被广泛称为KAM理论。为了应用KAM理论,我们通过推导多层感知器的梯度的覆盖数的估计来提供Hamilton神经网络的泛化误差界,这是模型的关键组成部分。该误差界给出了在KAM理论的应用中所需的哈密顿量上的$L^\infty$界。

英文摘要:

Many physical phenomena are described by Hamiltonian mechanics using an energy function (the Hamiltonian). Recently, the Hamiltonian neural network, which approximates the Hamiltonian as a neural network, and its extensions have attracted much attention. This is a very powerful method, but its use in theoretical studies remains limited. In this study, by combining the statistical learning theory and Kolmogorov-Arnold-Moser (KAM) theory, we provide a theoretical analysis of the behavior of Hamiltonian neural networks when the learning error is not completely zero. A Hamiltonian neural network with non-zero errors can be considered as a perturbation from the true dynamics, and the perturbation theory of the Hamilton equation is widely known as the KAM theory. To apply the KAM theory, we provide a generalization error bound for Hamiltonian neural networks by deriving an estimate of the covering number of the gradient of the multi-layer perceptron, which is the key ingredient of the model. This error bound gives an $L^\infty$ bound on the Hamiltonian that is required in the application of the KAM theory.

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。

↑