论基于神经网络的物理模拟器的不稳定性

Daniel Floryan
{"title":"论基于神经网络的物理模拟器的不稳定性","authors":"Daniel Floryan","doi":"arxiv-2406.13101","DOIUrl":null,"url":null,"abstract":"When neural networks are trained from data to simulate the dynamics of\nphysical systems, they encounter a persistent challenge: the long-time dynamics\nthey produce are often unphysical or unstable. We analyze the origin of such\ninstabilities when learning linear dynamical systems, focusing on the training\ndynamics. We make several analytical findings which empirical observations\nsuggest extend to nonlinear dynamical systems. First, the rate of convergence\nof the training dynamics is uneven and depends on the distribution of energy in\nthe data. As a special case, the dynamics in directions where the data have no\nenergy cannot be learned. Second, in the unlearnable directions, the dynamics\nproduced by the neural network depend on the weight initialization, and common\nweight initialization schemes can produce unstable dynamics. Third, injecting\nsynthetic noise into the data during training adds damping to the training\ndynamics and can stabilize the learned simulator, though doing so undesirably\nbiases the learned dynamics. For each contributor to instability, we suggest\nmitigative strategies. We also highlight important differences between learning\ndiscrete-time and continuous-time dynamics, and discuss extensions to nonlinear\nsystems.","PeriodicalId":501167,"journal":{"name":"arXiv - PHYS - Chaotic Dynamics","volume":"85 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"On instabilities in neural network-based physics simulators\",\"authors\":\"Daniel Floryan\",\"doi\":\"arxiv-2406.13101\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"When neural networks are trained from data to simulate the dynamics of\\nphysical systems, they encounter a persistent challenge: the long-time dynamics\\nthey produce are often unphysical or unstable. We analyze the origin of such\\ninstabilities when learning linear dynamical systems, focusing on the training\\ndynamics. We make several analytical findings which empirical observations\\nsuggest extend to nonlinear dynamical systems. First, the rate of convergence\\nof the training dynamics is uneven and depends on the distribution of energy in\\nthe data. As a special case, the dynamics in directions where the data have no\\nenergy cannot be learned. Second, in the unlearnable directions, the dynamics\\nproduced by the neural network depend on the weight initialization, and common\\nweight initialization schemes can produce unstable dynamics. Third, injecting\\nsynthetic noise into the data during training adds damping to the training\\ndynamics and can stabilize the learned simulator, though doing so undesirably\\nbiases the learned dynamics. For each contributor to instability, we suggest\\nmitigative strategies. We also highlight important differences between learning\\ndiscrete-time and continuous-time dynamics, and discuss extensions to nonlinear\\nsystems.\",\"PeriodicalId\":501167,\"journal\":{\"name\":\"arXiv - PHYS - Chaotic Dynamics\",\"volume\":\"85 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-06-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Chaotic Dynamics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2406.13101\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Chaotic Dynamics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2406.13101","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

当神经网络通过数据训练来模拟物理系统的动力学时,它们会遇到一个长期存在的挑战:它们产生的长期动力学往往是非物理的或不稳定的。我们分析了学习线性动力学系统时这种不稳定性的根源,重点关注训练动力学。我们得出了几项分析结论,经验观察表明,这些结论也适用于非线性动力系统。首先,训练动力学的收敛速度是不均匀的,取决于数据中能量的分布。作为一种特例,在数据没有能量的方向上的动力学是无法学习的。其次,在无法学习的方向上,神经网络产生的动态取决于权重初始化,而普通的权重初始化方案会产生不稳定的动态。第三,在训练过程中向数据中注入合成噪声会增加训练动力学的阻尼,并能稳定学习到的模拟器,但这样做会对学习到的动力学产生不良影响。针对每种不稳定因素,我们都提出了应对策略。我们还强调了学习离散时间和连续时间动力学之间的重要区别,并讨论了对非线性系统的扩展。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
On instabilities in neural network-based physics simulators
When neural networks are trained from data to simulate the dynamics of physical systems, they encounter a persistent challenge: the long-time dynamics they produce are often unphysical or unstable. We analyze the origin of such instabilities when learning linear dynamical systems, focusing on the training dynamics. We make several analytical findings which empirical observations suggest extend to nonlinear dynamical systems. First, the rate of convergence of the training dynamics is uneven and depends on the distribution of energy in the data. As a special case, the dynamics in directions where the data have no energy cannot be learned. Second, in the unlearnable directions, the dynamics produced by the neural network depend on the weight initialization, and common weight initialization schemes can produce unstable dynamics. Third, injecting synthetic noise into the data during training adds damping to the training dynamics and can stabilize the learned simulator, though doing so undesirably biases the learned dynamics. For each contributor to instability, we suggest mitigative strategies. We also highlight important differences between learning discrete-time and continuous-time dynamics, and discuss extensions to nonlinear systems.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Tunneling Time for Walking Droplets on an Oscillating Liquid Surface Rydberg excitons in cuprous oxide: A two-particle system with classical chaos Disruption of exo-asteroids around white dwarfs and the release of dust particles in debris rings in co-orbital motion Machine-aided guessing and gluing of unstable periodic orbits Nonequilibrium dynamics of coupled oscillators under the shear-velocity boundary condition
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1