{"id":"https://openalex.org/W7162025990","doi":"https://doi.org/10.48550/arxiv.2605.21108","title":"Efficient Learning of Deep State Space Models via Importance Smoothing","display_name":"Efficient Learning of Deep State Space Models via Importance Smoothing","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162025990","doi":"https://doi.org/10.48550/arxiv.2605.21108"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21108","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21108","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.21108","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108510861","display_name":"John-Joseph Brady","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brady, John-Joseph","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085251948","display_name":"Nikolas N\u00fcsken","orcid":"https://orcid.org/0000-0001-5415-5284"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nusken, Nikolas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136672925","display_name":"Yunpeng Li","orcid":"https://orcid.org/0000-0003-4798-541X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yunpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6341999769210815,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6341999769210815,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.07900000363588333,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.02879999950528145,"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/discriminative-model","display_name":"Discriminative model","score":0.7803000211715698},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.555400013923645},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5447999835014343},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5177000164985657},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5027999877929688},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4650000035762787},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4611000120639801},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.4375}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7803000211715698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6259999871253967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.612500011920929},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5051000118255615},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4611000120639801},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.4375},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40700000524520874},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C52918065","wikidata":"https://www.wikidata.org/wiki/Q230945","display_name":"State-space representation","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2718999981880188},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2685999870300293},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21108","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21108","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.21108","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21108","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":"article"},"sustainable_development_goals":[{"score":0.7772705554962158,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Latent":[0],"state":[1,22],"space":[2,23],"systems":[3],"are":[4,14],"ubiquitous":[5],"in":[6],"statistical":[7],"modelling,":[8],"arising":[9],"naturally":[10],"when":[11],"time":[12],"series":[13],"observed":[15],"through":[16,55],"noisy":[17],"measurements.":[18],"However,":[19],"training":[20,37,96,125],"deep":[21],"models":[24,45],"(DSSMs)":[25],"at":[26],"scale":[27,82],"remains":[28],"difficult.":[29],"Two":[30],"largely":[31],"distinct":[32],"strategies":[33],"have":[34],"emerged":[35],"for":[36,70,106],"DSSMs.":[38],"The":[39,52],"first,":[40],"auto-encoding":[41],"DSSMs,":[42],"trains":[43,104],"generative":[44,74,110],"by":[46],"optimising":[47],"a":[48,94,113],"variational":[49,90],"lower":[50],"bound.":[51],"second":[53],"backpropagates":[54],"the":[56,129],"outputs":[57],"of":[58,115],"classical":[59],"sequential":[60,79],"Monte":[61,91],"Carlo":[62],"(SMC)":[63],"algorithms.":[64],"Such":[65],"approaches":[66],"can":[67],"train":[68],"DSSMs":[69,105],"both":[71,107],"discriminative":[72,108],"and":[73,102,109],"tasks,":[75],"but":[76],"their":[77],"inherently":[78],"forward":[80],"passes":[81],"poorly":[83],"on":[84],"modern":[85],"hardware.":[86],"We":[87],"propose":[88],"\\emph{parallel":[89],"Carlo}":[92],"(PVMC),":[93],"new":[95],"method":[97],"that":[98],"bridges":[99],"these":[100],"paradigms":[101],"robustly":[103],"tasks.":[111],"Across":[112],"set":[114],"benchmark":[116],"experiments,":[117],"PVMC":[118],"matches":[119],"or":[120],"exceeds":[121],"state-of-the-art":[122],"performance":[123],"while":[124],"$10\\times$":[126],"faster":[127],"than":[128],"fastest":[130],"competing":[131],"SMC-based":[132],"approach.":[133]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-22T00:00:00"}