Neural DDEs with Learnable Delays for Partially Observed Dynamical Systems

Many successful methods to learn dynamical systems from data have recently been introduced. Such methods often rely on the availability of the system's full state. However, this underlying hypothesis is rather restrictive as it is typically not confirmed in practice, leaving us with partially o...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	arXiv.org 2024-10
Hauptverfasser:	Thibault Monsel, Menier, Emmanuel, Semeraro, Onofrio, Mathelin, Lionel, Charpiat, Guillaume
Format:	Artikel
Sprache:	eng
Schlagworte:	Differential equations Dynamical systems
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page
container_issue
container_start_page
container_title	arXiv.org
container_volume
creator	Thibault Monsel Menier, Emmanuel Semeraro, Onofrio Mathelin, Lionel Charpiat, Guillaume
description	Many successful methods to learn dynamical systems from data have recently been introduced. Such methods often rely on the availability of the system's full state. However, this underlying hypothesis is rather restrictive as it is typically not confirmed in practice, leaving us with partially observed systems. Utilizing the Mori-Zwanzig (MZ) formalism from statistical physics, we demonstrate that Constant Lag Neural Delay Differential Equations (NDDEs) naturally serve as suitable models for partially observed states. In empirical evaluation, we show that such models outperform existing methods on both synthetic and experimental data.
format	Article
fullrecord	<record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3113847129</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3113847129</sourcerecordid><originalsourceid>FETCH-proquest_journals_31138471293</originalsourceid><addsrcrecordid>eNqNjMEKgkAUAJcgSMp_WOgsuLuadk4jIiqouzzrScqqtW8t9u_z0Ad0msvMTJgnlRJBGkk5Yz5RE4ahXCUyjpXH9kccDGieZTnxT20f_IBgOig18gw1OOJVb_gZjK1Ba8dPJaF5451nroO2vo3txZHFlhZsWoEm9H-cs-U2v252wdP0rwHJFk0_jGtNhRJCpVEi5Fr9Z30BdG48RQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3113847129</pqid></control><display><type>article</type><title>Neural DDEs with Learnable Delays for Partially Observed Dynamical Systems</title><source>Free E- Journals</source><creator>Thibault Monsel ; Menier, Emmanuel ; Semeraro, Onofrio ; Mathelin, Lionel ; Charpiat, Guillaume</creator><creatorcontrib>Thibault Monsel ; Menier, Emmanuel ; Semeraro, Onofrio ; Mathelin, Lionel ; Charpiat, Guillaume</creatorcontrib><description>Many successful methods to learn dynamical systems from data have recently been introduced. Such methods often rely on the availability of the system's full state. However, this underlying hypothesis is rather restrictive as it is typically not confirmed in practice, leaving us with partially observed systems. Utilizing the Mori-Zwanzig (MZ) formalism from statistical physics, we demonstrate that Constant Lag Neural Delay Differential Equations (NDDEs) naturally serve as suitable models for partially observed states. In empirical evaluation, we show that such models outperform existing methods on both synthetic and experimental data.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Differential equations ; Dynamical systems</subject><ispartof>arXiv.org, 2024-10</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>778,782</link.rule.ids></links><search><creatorcontrib>Thibault Monsel</creatorcontrib><creatorcontrib>Menier, Emmanuel</creatorcontrib><creatorcontrib>Semeraro, Onofrio</creatorcontrib><creatorcontrib>Mathelin, Lionel</creatorcontrib><creatorcontrib>Charpiat, Guillaume</creatorcontrib><title>Neural DDEs with Learnable Delays for Partially Observed Dynamical Systems</title><title>arXiv.org</title><description>Many successful methods to learn dynamical systems from data have recently been introduced. Such methods often rely on the availability of the system's full state. However, this underlying hypothesis is rather restrictive as it is typically not confirmed in practice, leaving us with partially observed systems. Utilizing the Mori-Zwanzig (MZ) formalism from statistical physics, we demonstrate that Constant Lag Neural Delay Differential Equations (NDDEs) naturally serve as suitable models for partially observed states. In empirical evaluation, we show that such models outperform existing methods on both synthetic and experimental data.</description><subject>Differential equations</subject><subject>Dynamical systems</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjMEKgkAUAJcgSMp_WOgsuLuadk4jIiqouzzrScqqtW8t9u_z0Ad0msvMTJgnlRJBGkk5Yz5RE4ahXCUyjpXH9kccDGieZTnxT20f_IBgOig18gw1OOJVb_gZjK1Ba8dPJaF5451nroO2vo3txZHFlhZsWoEm9H-cs-U2v252wdP0rwHJFk0_jGtNhRJCpVEi5Fr9Z30BdG48RQ</recordid><startdate>20241003</startdate><enddate>20241003</enddate><creator>Thibault Monsel</creator><creator>Menier, Emmanuel</creator><creator>Semeraro, Onofrio</creator><creator>Mathelin, Lionel</creator><creator>Charpiat, Guillaume</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241003</creationdate><title>Neural DDEs with Learnable Delays for Partially Observed Dynamical Systems</title><author>Thibault Monsel ; Menier, Emmanuel ; Semeraro, Onofrio ; Mathelin, Lionel ; Charpiat, Guillaume</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31138471293</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Differential equations</topic><topic>Dynamical systems</topic><toplevel>online_resources</toplevel><creatorcontrib>Thibault Monsel</creatorcontrib><creatorcontrib>Menier, Emmanuel</creatorcontrib><creatorcontrib>Semeraro, Onofrio</creatorcontrib><creatorcontrib>Mathelin, Lionel</creatorcontrib><creatorcontrib>Charpiat, Guillaume</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Thibault Monsel</au><au>Menier, Emmanuel</au><au>Semeraro, Onofrio</au><au>Mathelin, Lionel</au><au>Charpiat, Guillaume</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Neural DDEs with Learnable Delays for Partially Observed Dynamical Systems</atitle><jtitle>arXiv.org</jtitle><date>2024-10-03</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Many successful methods to learn dynamical systems from data have recently been introduced. Such methods often rely on the availability of the system's full state. However, this underlying hypothesis is rather restrictive as it is typically not confirmed in practice, leaving us with partially observed systems. Utilizing the Mori-Zwanzig (MZ) formalism from statistical physics, we demonstrate that Constant Lag Neural Delay Differential Equations (NDDEs) naturally serve as suitable models for partially observed states. In empirical evaluation, we show that such models outperform existing methods on both synthetic and experimental data.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext	fulltext
identifier	EISSN: 2331-8422
ispartof	arXiv.org, 2024-10
issn	2331-8422
language	eng
recordid	cdi_proquest_journals_3113847129
source	Free E- Journals
subjects	Differential equations Dynamical systems
title	Neural DDEs with Learnable Delays for Partially Observed Dynamical Systems
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T21%3A58%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Neural%20DDEs%20with%20Learnable%20Delays%20for%20Partially%20Observed%20Dynamical%20Systems&rft.jtitle=arXiv.org&rft.au=Thibault%20Monsel&rft.date=2024-10-03&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3113847129%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3113847129&rft_id=info:pmid/&rfr_iscdi=true