{"title":"非线性动力学的分布式深度库普曼学习","authors":"Wenjian Hao, Lili Wang, Ayush Rai, Shaoshuai Mou","doi":"arxiv-2409.11586","DOIUrl":null,"url":null,"abstract":"Koopman operator theory has proven to be highly significant in system\nidentification, even for challenging scenarios involving nonlinear time-varying\nsystems (NTVS). In this context, we examine a network of connected agents, each\nwith limited observation capabilities, aiming to estimate the dynamics of an\nNTVS collaboratively. Drawing inspiration from Koopman operator theory, deep\nneural networks, and distributed consensus, we introduce a distributed\nalgorithm for deep Koopman learning of the dynamics of an NTVS. This approach\nenables individual agents to approximate the entire dynamics despite having\naccess to only partial state observations. We guarantee consensus not only on\nthe estimated dynamics but also on its structure, i.e., the matrices\nencountered in the linear equation of the lifted Koopman system. We provide\ntheoretical insights into the convergence of the learning process and\naccompanying numerical simulations.","PeriodicalId":501175,"journal":{"name":"arXiv - EE - Systems and Control","volume":"37 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Distributed Deep Koopman Learning for Nonlinear Dynamics\",\"authors\":\"Wenjian Hao, Lili Wang, Ayush Rai, Shaoshuai Mou\",\"doi\":\"arxiv-2409.11586\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Koopman operator theory has proven to be highly significant in system\\nidentification, even for challenging scenarios involving nonlinear time-varying\\nsystems (NTVS). In this context, we examine a network of connected agents, each\\nwith limited observation capabilities, aiming to estimate the dynamics of an\\nNTVS collaboratively. Drawing inspiration from Koopman operator theory, deep\\nneural networks, and distributed consensus, we introduce a distributed\\nalgorithm for deep Koopman learning of the dynamics of an NTVS. This approach\\nenables individual agents to approximate the entire dynamics despite having\\naccess to only partial state observations. We guarantee consensus not only on\\nthe estimated dynamics but also on its structure, i.e., the matrices\\nencountered in the linear equation of the lifted Koopman system. We provide\\ntheoretical insights into the convergence of the learning process and\\naccompanying numerical simulations.\",\"PeriodicalId\":501175,\"journal\":{\"name\":\"arXiv - EE - Systems and Control\",\"volume\":\"37 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Systems and Control\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11586\",\"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 - EE - Systems and Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11586","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Distributed Deep Koopman Learning for Nonlinear Dynamics
Koopman operator theory has proven to be highly significant in system
identification, even for challenging scenarios involving nonlinear time-varying
systems (NTVS). In this context, we examine a network of connected agents, each
with limited observation capabilities, aiming to estimate the dynamics of an
NTVS collaboratively. Drawing inspiration from Koopman operator theory, deep
neural networks, and distributed consensus, we introduce a distributed
algorithm for deep Koopman learning of the dynamics of an NTVS. This approach
enables individual agents to approximate the entire dynamics despite having
access to only partial state observations. We guarantee consensus not only on
the estimated dynamics but also on its structure, i.e., the matrices
encountered in the linear equation of the lifted Koopman system. We provide
theoretical insights into the convergence of the learning process and
accompanying numerical simulations.