{"id":"https://openalex.org/W7161568949","doi":"https://doi.org/10.48550/arxiv.2605.16048","title":"Looped SSMs: Depth-Recurrence and Input Reshaping for Time Series Classification","display_name":"Looped SSMs: Depth-Recurrence and Input Reshaping for Time Series Classification","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161568949","doi":"https://doi.org/10.48550/arxiv.2605.16048"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.16048","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16048","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":null,"license_id":null,"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.2605.16048","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085278461","display_name":"M\u00f3nika Farsang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farsang, M\u00f3nika","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124894075","display_name":"Ramin Hasani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hasani, Ramin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127835665","display_name":"Daniela Rus","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rus, Daniela","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034362557","display_name":"Radu Grosu","orcid":"https://orcid.org/0000-0001-5715-2142"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grosu, Radu","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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.8040000200271606,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.8040000200271606,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.05260000005364418,"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"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.009499999694526196,"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/iterated-function","display_name":"Iterated function","score":0.5515000224113464},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/flattening","display_name":"Flattening","score":0.4675999879837036},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4253000020980835},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.40869998931884766},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.3102000057697296},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.30000001192092896}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6110000014305115},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.5515000224113464},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C19444555","wikidata":"https://www.wikidata.org/wiki/Q212750","display_name":"Flattening","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.453900009393692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43050000071525574},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3224000036716461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C92811239","wikidata":"https://www.wikidata.org/wiki/Q20998670","display_name":"Expressivity","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.16048","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16048","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.16048","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16048","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"State":[0],"Space":[1],"Models":[2],"(SSMs)":[3],"are":[4,190],"inherently":[5],"recurrent":[6],"along":[7],"the":[8,15,88,92,155],"sequence":[9],"dimension,":[10],"yet":[11],"depth-recurrence":[12,126],"-":[13,27],"reusing":[14],"same":[16],"block":[17],"repeatedly":[18],"across":[19,62,112,167],"layers,":[20],"as":[21,83,95,114],"recently":[22],"applied":[23],"in":[24,32],"looped":[25,40,93],"transformers":[26],"has":[28],"not":[29],"been":[30],"explored":[31],"this":[33,99],"model":[34,90,94],"family.":[35],"We":[36,134],"show":[37,136],"that":[38,119,125,137,180,185],"a":[39,53,78,96,115],"SSM":[41,55],"with":[42,56],"$k$":[43],"parameters":[44,61],"iterated":[45],"$L$":[46],"times":[47],"consistently":[48],"closely":[49],"matches":[50],"or":[51,151],"outperforms":[52],"standard":[54],"$k":[57],"\\cdot":[58],"L$":[59],"independent":[60,192],"four":[63],"architectures":[64],"(LRU,":[65],"S5,":[66],"LinOSS,":[67],"LrcSSM)":[68],"and":[69,106,131,153,187,193],"six":[70],"time":[71,200],"series":[72],"classification":[73],"benchmarks,":[74],"despite":[75],"operating":[76],"within":[77],"strictly":[79],"smaller":[80],"hypothesis":[81],"space,":[82],"we":[84],"formally":[85],"establish.":[86],"Since":[87],"larger":[89],"contains":[91],"special":[97],"case,":[98],"dominance":[100],"cannot":[101],"be":[102],"explained":[103],"by":[104],"expressivity":[105],"instead":[107],"points":[108],"to":[109,129],"parameter":[110],"sharing":[111],"depth":[113,186],"beneficial":[116],"inductive":[117],"bias":[118],"simplifies":[120],"optimization.":[121],"These":[122],"results":[123],"demonstrate":[124],"is":[127,140],"orthogonal":[128],"sequence-recurrence":[130],"independently":[132],"beneficial.":[133],"further":[135],"input":[138,188],"reshaping":[139,189],"an":[141],"equally":[142],"neglected":[143],"design":[144,195],"axis:":[145],"concatenating":[146],"timesteps":[147],"for":[148,159,197],"low-dimensional":[149],"inputs,":[150],"flattening":[152],"rechunking":[154],"joint":[156],"feature-time":[157],"dimension":[158],"high-dimensional":[160],"ones,":[161],"yields":[162],"accuracy":[163],"gains":[164],"of":[165],"1-6%":[166],"all":[168],"models,":[169],"confirmed":[170],"over":[171],"5":[172],"random":[173],"seeds.":[174],"Both":[175],"techniques":[176],"provide":[177],"standalone":[178],"improvements":[179],"compound":[181],"when":[182],"combined,":[183],"suggesting":[184],"two":[191],"underexplored":[194],"axes":[196],"SSMs":[198],"on":[199],"series.":[201]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-19T00:00:00"}