{"id":"https://openalex.org/W7130388304","doi":"https://doi.org/10.48550/arxiv.2602.15649","title":"Continuous-Time Piecewise-Linear Recurrent Neural Networks","display_name":"Continuous-Time Piecewise-Linear Recurrent Neural Networks","publication_year":2026,"publication_date":"2026-02-17","ids":{"openalex":"https://openalex.org/W7130388304","doi":"https://doi.org/10.48550/arxiv.2602.15649"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.15649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.15649","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114655384","display_name":"Alena Br\u00e4ndle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Br\u00e4ndle, Alena","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093136109","display_name":"Lukas Eisenmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eisenmann, Lukas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126303797","display_name":"Florian G\u00f6tz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G\u00f6tz, Florian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056788018","display_name":"Daniel Durstewitz","orcid":"https://orcid.org/0000-0002-9340-3786"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Durstewitz, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.4302999973297119,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.4302999973297119,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12536","display_name":"Topological and Geometric Data Analysis","score":0.19030000269412994,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.06459999829530716,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.6000000238418579},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5536999702453613},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5403000116348267},{"id":"https://openalex.org/keywords/classification-of-discontinuities","display_name":"Classification of discontinuities","score":0.506600022315979},{"id":"https://openalex.org/keywords/dynamical-systems-theory","display_name":"Dynamical systems theory","score":0.501800000667572},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47929999232292175},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4602000117301941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6140000224113464},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.6000000238418579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5568000078201294},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5403000116348267},{"id":"https://openalex.org/C15627037","wikidata":"https://www.wikidata.org/wiki/Q541961","display_name":"Classification of discontinuities","level":2,"score":0.506600022315979},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C33962884","wikidata":"https://www.wikidata.org/wiki/Q378637","display_name":"Dynamical system (definition)","level":3,"score":0.4302000105381012},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3743000030517578},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32499998807907104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31380000710487366},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.15649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.15649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.863111138343811}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,39],"dynamical":[1,10],"systems":[2,214],"reconstruction":[3],"(DSR)":[4],"we":[5,18,58,151],"aim":[6,19],"to":[7,20,49,61,122,200],"recover":[8],"the":[9,28,65,108,140],"system":[11],"(DS)":[12],"underlying":[13],"observed":[14],"time":[15],"series.":[16],"Specifically,":[17],"learn":[21],"a":[22,75,160],"generative":[23],"surrogate":[24],"model":[25],"which":[26,217],"approximates":[27],"underlying,":[29],"data-generating":[30],"DS,":[31],"and":[32,41,115,118,145,165],"recreates":[33],"its":[34],"long-term":[35],"properties":[36],"(`climate":[37],"statistics').":[38],"scientific":[40],"medical":[42],"areas,":[43],"in":[44,78,105,194],"particular,":[45],"these":[46],"models":[47,84],"need":[48],"be":[50,191],"mechanistically":[51],"tractable":[52],"--":[53],"through":[54],"their":[55,92,148,175,202],"mathematical":[56,87],"analysis":[57],"would":[59],"like":[60,185],"obtain":[62],"insight":[63,88],"into":[64],"recovered":[66],"system's":[67],"workings.":[68],"Piecewise-linear":[69],"(PL),":[70],"ReLU-based":[71],"RNNs":[72],"(PLRNNs)":[73],"have":[74],"strong":[76],"track-record":[77],"this":[79],"regard,":[80],"representing":[81],"SOTA":[82],"DSR":[83,141,211],"while":[85],"allowing":[86],"by":[89,172],"virtue":[90],"of":[91,112,143],"PL":[93,176],"design.":[94],"However,":[95],"all":[96],"current":[97],"PLRNN":[98],"variants":[99],"are":[100,132],"discrete-time":[101,203],"maps.":[102],"This":[103],"is":[104],"disaccord":[106],"with":[107,215,219],"assumed":[109],"continuous-time":[110,155],"nature":[111],"most":[113],"physical":[114],"biological":[116],"processes,":[117],"makes":[119],"it":[120],"hard":[121,220],"accommodate":[123],"data":[124],"arriving":[125],"at":[126],"irregular":[127],"temporal":[128],"intervals.":[129],"Neural":[130,208],"ODEs":[131,209],"one":[133],"solution,":[134],"but":[135],"they":[136],"do":[137],"not":[138],"reach":[139],"performance":[142],"PLRNNs":[144,156],"often":[146],"lack":[147],"tractability.":[149],"Here":[150],"develop":[152],"theory":[153],"for":[154,163],"(cPLRNNs):":[157],"We":[158,178,197],"present":[159],"novel":[161],"algorithm":[162],"training":[164],"simulating":[166],"such":[167],"models,":[168],"bypassing":[169],"numerical":[170],"integration":[171],"efficiently":[173],"exploiting":[174],"structure.":[177],"further":[179],"demonstrate":[180],"how":[181],"important":[182],"topological":[183],"objects":[184],"equilibria":[186],"or":[187],"limit":[188],"cycles":[189],"can":[190],"determined":[192],"semi-analytically":[193],"trained":[195],"models.":[196],"compare":[198],"cPLRNNs":[199],"both":[201],"cousins":[204],"as":[205,207],"well":[206],"on":[210],"benchmarks,":[212],"including":[213],"discontinuities":[216],"come":[218],"thresholds.":[221]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-19T00:00:00"}