{"id":"https://openalex.org/W7212111980","doi":"https://doi.org/10.48550/arxiv.2609.09586","title":"Distillation of Synthetic Data for Time Series Foundation Models","display_name":"Distillation of Synthetic Data for Time Series Foundation Models","publication_year":2026,"publication_date":"2026-09-09","ids":{"openalex":"https://openalex.org/W7212111980","doi":"https://doi.org/10.48550/arxiv.2609.09586"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.09586","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.09586","pdf_url":"https://arxiv.org/pdf/2609.09586","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/2609.09586","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126557367","display_name":"Niloy Biswas","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biswas, Niloy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073887573","display_name":"Noureddine El Karoui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karoui, Noureddine El","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":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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9541000127792358,"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":0.9541000127792358,"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":0.010700000450015068,"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/T10320","display_name":"Neural Networks and Applications","score":0.006000000052154064,"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/time-series-foundation-models","display_name":"time series foundation models","score":0.9390000104904175},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.515999972820282},{"id":"https://openalex.org/keywords/rao-blackwellization","display_name":"Rao-Blackwellization","score":0.9779999852180481}],"concepts":[{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.6366000175476074},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.6111999750137329},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5756999850273132},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.48350000381469727},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37439998984336853},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.328000009059906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3273000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.09586","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.09586","pdf_url":"https://arxiv.org/pdf/2609.09586","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.2609.09586","doi":"https://doi.org/10.48550/arxiv.2609.09586","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.09586","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:2609.09586","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.09586","pdf_url":"https://arxiv.org/pdf/2609.09586","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212111980.pdf","grobid_xml":"https://content.openalex.org/works/W7212111980.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417285558","https://openalex.org/W4392539490","https://openalex.org/W7125966464","https://openalex.org/W4417113063","https://openalex.org/W4417117990","https://openalex.org/W7164129011","https://openalex.org/W7214931272","https://openalex.org/W7102564449","https://openalex.org/W7125352578","https://openalex.org/W7106511712"],"abstract_inverted_index":{"Time":[0],"series":[1,12],"foundation":[2],"models":[3],"(TSFMs)":[4],"are":[5,24],"increasingly":[6],"pre-trained":[7],"on":[8,26,102,125],"synthetically":[9],"generated":[10],"time":[11],"trajectories,":[13],"where":[14],"the":[15,50,71,78,87,90,94,134],"data":[16,62],"generating":[17],"process":[18],"is":[19],"known.":[20],"Current":[21],"pre-training":[22],"recipes":[23],"based":[25],"loss":[27,43,120,137],"objectives":[28,44],"which":[29,45],"compare":[30,46],"TSFM":[31,47,104],"outputs":[32,48],"to":[33,49,67,111],"realized":[34],"future":[35],"values":[36],"of":[37,54,70,80,89,107,118],"each":[38,55],"trajectory.":[39],"We":[40,98],"instead":[41],"propose":[42],"conditional":[51],"forecast":[52],"distribution":[53],"trajectory,":[56],"a":[57,68,103],"procedure":[58],"we":[59],"call":[60],"synthetic":[61],"distillation":[63],"(SDD).":[64],"SDD":[65,101,129],"corresponds":[66],"Rao-Blackwellization":[69],"training":[72,142],"objective,":[73],"in":[74],"that":[75],"it":[76],"leaves":[77],"expectation":[79],"stochastic":[81,91],"gradients":[82],"unchanged":[83],"while":[84],"provably":[85],"reducing":[86],"covariance":[88],"gradient":[92],"under":[93],"Loewner":[95],"partial":[96],"ordering.":[97],"empirically":[99],"validate":[100],"model":[105,123],"family":[106],"sizes":[108],"from":[109],"$4$M":[110],"$2.5$B":[112],"parameters,":[113],"and":[114],"observe":[115],"faster":[116],"convergence":[117],"validation":[119],"at":[121],"every":[122],"size:":[124],"Gaussian":[126],"Process":[127],"data,":[128],"attains":[130],"or":[131],"improves":[132],"upon":[133],"Status":[135],"Quo":[136],"whilst":[138],"requiring":[139],"$10\\%-40\\%$":[140],"less":[141],"iterations.":[143]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-09-11T00:00:00"}