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 2403.08690math.OC
收藏

连续网络的可控性与基于核学习的逼近方法

Controllability of continuous networks and a kernel-based learning approximation

Michael Herty, Chiara Segala, Giuseppe Visconti

AI总结:

该研究将残差深度神经网络建模为平均场动力学,利用希尔伯特唯一性方法证明可控性,并提出基于核学习的数值求解训练问题的高效方法。

摘要:

残差深度神经网络被表述为相互作用的粒子系统,从而通过神经微分方程进行描述,并且在输入数据规模较大的情况下,通过平均场神经网络进行描述。平均场描述还允许将训练过程重新表述为平均场动力学解的可控性问题。我们通过希尔伯特唯一性方法展示了线性微观动力学和平均场动力学的可控性理论结果,并提出了一种基于核学习方法的计算途径,以高效地数值求解训练问题。此外,还将回顾平均场方程结构性质的进一步方面。

英文摘要:

Residual deep neural networks are formulated as interacting particle systems leading to a description through neural differential equations, and, in the case of large input data, through mean-field neural networks. The mean-field description allows also the recast of the training processes as a controllability problem for the solution to the mean-field dynamics. We show theoretical results on the controllability of the linear microscopic and mean-field dynamics through the Hilbert Uniqueness Method and propose a computational approach based on kernel learning methods to solve numerically, and efficiently, the training problem. Further aspects of the structural properties of the mean-field equation will be reviewed.

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。

↑