{"id":"https://openalex.org/W7147610613","doi":"https://doi.org/10.48550/arxiv.2603.27814","title":"RG-TTA: Regime-Guided Meta-Control for Test-Time Adaptation in Streaming Time Series","display_name":"RG-TTA: Regime-Guided Meta-Control for Test-Time Adaptation in Streaming Time Series","publication_year":2026,"publication_date":"2026-03-29","ids":{"openalex":"https://openalex.org/W7147610613","doi":"https://doi.org/10.48550/arxiv.2603.27814"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.27814","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27814","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.2603.27814","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109534834","display_name":"Indar Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Indar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132684080","display_name":"Akanksha Tiwari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiwari, Akanksha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132635800","display_name":"Sai Krishna Jasti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jasti, Sai Krishna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132622648","display_name":"Ankit Hemant Lade","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lade, Ankit Hemant","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/T13702","display_name":"Machine Learning in Healthcare","score":0.2207999974489212,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.2207999974489212,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.12319999933242798,"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":0.09139999747276306,"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/adaptation","display_name":"Adaptation (eye)","score":0.6152999997138977},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.583899974822998},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.40149998664855957},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3955000042915344},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.3905999958515167},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.37049999833106995},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3610999882221222},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.35659998655319214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372000217437744},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6152999997138977},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3610999882221222},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3528999984264374},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3450999855995178},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3077999949455261},{"id":"https://openalex.org/C93038891","wikidata":"https://www.wikidata.org/wiki/Q1061524","display_name":"Intensity (physics)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.27814","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27814","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.2603.27814","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27814","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Test-time":[0],"adaptation":[1,21,41],"(TTA)":[2],"enables":[3],"neural":[4],"forecasters":[5],"to":[6,8,47,72,106],"adapt":[7],"distribution":[9],"shifts":[10],"in":[11,226],"streaming":[12,210],"time":[13],"series,":[14],"but":[15],"existing":[16],"methods":[17],"apply":[18],"the":[19,25,28,76,104,109,135,223],"same":[20],"intensity":[22,42],"regardless":[23],"of":[24,27,53,228],"nature":[26],"shift.":[29],"We":[30,160],"propose":[31],"Regime-Guided":[32],"Test-Time":[33],"Adaptation":[34],"(RG-TTA),":[35],"a":[36,62,115,123,209],"meta-controller":[37],"that":[38],"continuously":[39],"modulates":[40],"based":[43],"on":[44],"distributional":[45],"similarity":[46,63],"previously-seen":[48],"regimes.":[49],"Using":[50],"an":[51],"ensemble":[52],"Kolmogorov-Smirnov,":[54],"Wasserstein-1,":[55],"feature-distance,":[56],"and":[57,69,90,145,154,167,170,200,237],"variance-ratio":[58],"metrics,":[59],"RG-TTA":[60,118,142,238,242],"computes":[61],"score":[64],"for":[65,82,86],"each":[66,111],"incoming":[67],"batch":[68,112],"uses":[70],"it":[71,147],"(i)":[73],"smoothly":[74],"scale":[75],"learning":[77],"rate":[78],"--":[79,89,164,169],"more":[80],"aggressive":[81],"novel":[83],"distributions,":[84],"conservative":[85],"familiar":[87],"ones":[88],"(ii)":[91],"control":[92],"gradient":[93],"effort":[94,110],"via":[95],"loss-driven":[96],"early":[97],"stopping":[98],"rather":[99],"than":[100],"fixed":[101],"budgets,":[102],"allowing":[103],"system":[105],"allocate":[107],"exactly":[108],"requires.":[113],"As":[114],"supplementary":[116],"mechanism,":[117],"gates":[119],"checkpoint":[120],"reuse":[121],"from":[122],"regime":[124,198],"memory,":[125],"loading":[126],"stored":[127],"specialist":[128],"models":[129],"only":[130],"when":[131],"they":[132],"demonstrably":[133],"outperform":[134],"current":[136],"model":[137],"(loss":[138],"improvement":[139],">=":[140],"30%).":[141],"is":[143],"model-agnostic":[144],"strategy-composable:":[146],"wraps":[148],"any":[149,156],"forecaster":[150],"exposing":[151],"train/predict/save/load":[152],"interfaces":[153],"enhances":[155],"gradient-based":[157],"TTA":[158,248],"method.":[159],"demonstrate":[161],"three":[162],"compositions":[163],"RG-TTA,":[165],"RG-EWC,":[166],"RG-DynaTTA":[168],"evaluate":[171],"6":[172],"update":[173],"policies":[174,221],"(3":[175],"baselines":[176],"+":[177,195],"3":[178,214],"regime-guided":[179],"variants)":[180],"across":[181],"4":[182,201],"compact":[183],"architectures":[184],"(GRU,":[185],"iTransformer,":[186],"PatchTST,":[187],"DLinear),":[188],"14":[189],"datasets":[190],"(6":[191],"real-world":[192],"multivariate":[193],"benchmarks":[194],"8":[196],"synthetic":[197],"scenarios),":[199],"forecast":[202],"horizons":[203],"(96,":[204],"192,":[205],"336,":[206],"720)":[207],"under":[208],"evaluation":[211],"protocol":[212],"with":[213,233],"random":[215],"seeds":[216],"(672":[217],"experiments":[218,231],"total).":[219],"Regime-guided":[220],"achieve":[222],"lowest":[224],"MSE":[225,244,255],"156":[227],"224":[229],"seed-averaged":[230],"(69.6%),":[232],"RG-EWC":[234,253],"winning":[235,239],"30.4%":[236],"29.0%.":[240],"Overall,":[241],"reduces":[243,254],"by":[245,256],"5.7%":[246],"vs":[247,258],"while":[249],"running":[250],"5.5%":[251],"faster;":[252],"14.1%":[257],"standalone":[259],"EWC.":[260]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-02T00:00:00"}