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 2407.17092math.NAcs.NA
收藏

通过半自主神经ODE实现动力系统通用逼近及其应用

Universal Approximation of Dynamical Systems by Semi-Autonomous Neural ODEs and Applications

Jilin University(吉林大学);Friedrich–Alexander-Universität Erlangen–Nürnberg(埃尔朗根-纽伦堡大学);Université Bourgogne Europe, CNRS(勃艮第欧洲大学,法国国家科学研究中心);Universidad Autónoma de Madrid(马德里自治大学);Fundación Deusto(德乌斯托基金会)

Ziqian Li, Kang Liu, Lorenzo Liverani, Enrique Zuazua

AI总结:

本文提出半自主神经ODE,通过减少参数实现对动力系统的通用逼近,并验证其在捕捉ODE系统和传输方程动态方面的有效性。

摘要:

本文介绍了半自主神经普通微分方程(SA-NODEs),这是一种比普通NODEs参数更少的变种。我们从理论和数值角度研究SA-NODEs对动力系统的通用逼近性质。在有限时间 horizon 的假设下,在一般假设下,我们建立了渐近逼近结果,证明当参数数量趋于无穷时误差消失。在额外的正则性假设下,我们进一步指定了该收敛速度与参数数量的关系,利用Barron空间中的定量逼近结果。基于先前结果,我们证明了通过其神经对应物对传输方程的逼近速度。我们的数值实验验证了SA-NODEs在捕捉各种ODE系统和传输方程动态方面的有效性。此外,我们比较了SA-NODEs与普通NODEs,突显了我们方法的优越性能和较低的复杂度。

英文摘要:

In this paper, we introduce semi-autonomous neural ordinary differential equations (SA-NODEs), a variation of the vanilla NODEs, employing fewer parameters. We investigate the universal approximation properties of SA-NODEs for dynamical systems from both a theoretical and a numerical perspective. Within the assumption of a finite-time horizon, under general hypotheses we establish an asymptotic approximation result, demonstrating that the error vanishes as the number of parameters goes to infinity. Under additional regularity assumptions, we further specify this convergence rate in relation to the number of parameters, utilizing quantitative approximation results in the Barron space. Based on the previous result, we prove an approximation rate for transport equations by their neural counterparts. Our numerical experiments validate the effectiveness of SA-NODEs in capturing the dynamics of various ODE systems and transport equations. Additionally, we compare SA-NODEs with vanilla NODEs, highlighting the superior performance and reduced complexity of our approach.

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。

↑