{"id":"https://openalex.org/W7220400330","doi":"https://doi.org/10.48550/arxiv.2610.02659","title":"Distributed Learning with Selective State Space Models: Architecture-Aware Convergence Analysis","display_name":"Distributed Learning with Selective State Space Models: Architecture-Aware Convergence Analysis","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7220400330","doi":"https://doi.org/10.48550/arxiv.2610.02659"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.02659","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.02659","pdf_url":"https://arxiv.org/pdf/2610.02659","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.02659","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092130671","display_name":"Adam Piaseczny","orcid":"https://orcid.org/0009-0001-8622-5467","observed_orcids":["https://orcid.org/0009-0001-8622-5467"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piaseczny, Adam","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009000462","display_name":"Md Kamran Chowdhury Shisher","orcid":"https://orcid.org/0000-0002-3991-1130","observed_orcids":["https://orcid.org/0000-0002-3991-1130"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shisher, Md Kamran Chowdhury","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157600148","display_name":"Shiqiang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wang, Shiqiang","raw_affiliation_strings":["University of Exeter"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Exeter","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020399355","display_name":"Christopher G. Brinton","orcid":"https://orcid.org/0000-0003-2771-3521","observed_orcids":["https://orcid.org/0000-0003-2771-3521"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brinton, Christopher G.","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9945999979972839,"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"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9945999979972839,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0038999998942017555,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0003000000142492354,"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/selective-state-space-models","display_name":"selective state space models","score":0.843999981880188},{"id":"https://openalex.org/keywords/federated-learning","display_name":"federated learning","score":0.8209999799728394},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.8820000290870667},{"id":"https://openalex.org/keywords/fedavg","display_name":"FedAvg","score":0.8370000123977661},{"id":"https://openalex.org/keywords/fedprox","display_name":"FedProx","score":1.0},{"id":"https://openalex.org/keywords/gradient-bounds","display_name":"gradient bounds","score":0.7229999899864197},{"id":"https://openalex.org/keywords/client-heterogeneity","display_name":"client heterogeneity","score":0.8629999756813049},{"id":"https://openalex.org/keywords/mamba-2","display_name":"Mamba-2","score":0.9210000038146973},{"id":"https://openalex.org/keywords/language-modeling","display_name":"language modeling","score":0.6119999885559082},{"id":"https://openalex.org/keywords/sequence-modeling","display_name":"sequence modeling","score":0.5059999823570251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6848000288009644},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.6428999900817871},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5608000159263611},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4814000129699707},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3898000121116638},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3790999948978424},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C52918065","wikidata":"https://www.wikidata.org/wiki/Q230945","display_name":"State-space representation","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.02659","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.02659","pdf_url":"https://arxiv.org/pdf/2610.02659","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.02659","doi":"https://doi.org/10.48550/arxiv.2610.02659","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.02659","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.02659","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.02659","pdf_url":"https://arxiv.org/pdf/2610.02659","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220400330.pdf","grobid_xml":"https://content.openalex.org/works/W7220400330.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4407174748","https://openalex.org/W6885029192","https://openalex.org/W4414122591","https://openalex.org/W7213528995","https://openalex.org/W3174087000","https://openalex.org/W7108207754","https://openalex.org/W4393161053","https://openalex.org/W3095381281","https://openalex.org/W7129105294","https://openalex.org/W7214774333"],"abstract_inverted_index":{"Modern":[0],"state":[1,92],"space":[2],"models":[3],"(SSMs),":[4],"such":[5],"as":[6],"Mamba2,":[7],"provide":[8,161],"a":[9,109,113,162],"compelling":[10],"alternative":[11],"to":[12,124],"transformers":[13],"by":[14,108,140],"combining":[15],"linear-time":[16],"sequence":[17],"modeling":[18,149],"with":[19],"recurrent":[20,87],"state-space":[21,55],"dynamics.":[22],"However,":[23],"the":[24,37,51,102,117,128,166],"behavior":[25,167],"of":[26,130,168],"SSMs":[27],"in":[28],"distributed":[29],"learning":[30,41,144,171],"settings":[31],"remains":[32],"poorly":[33],"understood.":[34],"In":[35],"particular,":[36],"existing":[38],"standard":[39],"federated":[40,96,143,170],"methods":[42],"are":[43],"largely":[44],"architecture-agnostic,":[45],"and":[46,54,69,74,78,83,91,133,136],"do":[47],"not":[48],"account":[49],"for":[50,72,81,164],"stability,":[52,88],"selectivity,":[53],"parameterization":[56],"that":[57,115],"characterize":[58],"modern":[59],"selective":[60,76],"SSMs.":[61],"To":[62],"address":[63],"this,":[64],"we":[65],"derive":[66],"architecture-aware":[67],"gradient":[68],"smoothness":[70],"bounds":[71,80,104,159],"single-":[73],"multi-layer":[75],"SSMs,":[77],"convergence":[79],"FedAvg":[82],"FedProx,":[84],"characterizing":[85],"how":[86,157],"input-dependent":[89],"discretization,":[90],"projection":[93],"norms":[94],"affect":[95],"optimization.":[97],"We":[98,120],"then":[99],"numerically":[100],"validate":[101],"single-layer":[103],"on":[105,146],"sequences":[106],"generated":[107],"teacher":[110],"SSM,":[111],"using":[112],"learner":[114],"follows":[116],"analyzed":[118],"recurrence.":[119],"use":[121],"this":[122],"analysis":[123],"formulate":[125],"expectations":[126,139],"about":[127],"effects":[129],"local":[131],"training":[132],"client":[134],"heterogeneity,":[135],"examine":[137],"these":[138],"comparing":[141],"nine":[142],"algorithms":[145],"Mamba2":[147],"language":[148],"across":[150],"six":[151],"text":[152],"domains.":[153],"These":[154],"experiments":[155],"illustrate":[156],"SSM-specific":[158],"can":[160],"basis":[163],"interpreting":[165],"practical":[169],"algorithms.":[172]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-06T00:00:00"}