{"id":"https://openalex.org/W6910423512","doi":"https://doi.org/10.48550/arxiv.2410.03935","title":"GAS-Norm: Score-Driven Adaptive Normalization for Non-Stationary Time Series Forecasting in Deep Learning","display_name":"GAS-Norm: Score-Driven Adaptive Normalization for Non-Stationary Time Series Forecasting in Deep Learning","publication_year":2024,"publication_date":"2024-10-04","ids":{"openalex":"https://openalex.org/W6910423512","doi":"https://doi.org/10.48550/arxiv.2410.03935"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2410.03935","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.03935","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":"article-journal"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2410.03935","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Urettini, Edoardo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Urettini, Edoardo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Atzeni, Daniele","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atzeni, Daniele","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ramjattan, Reshawn J.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramjattan, Reshawn J.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Carta, Antonio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carta, Antonio","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":true,"primary_topic":{"id":"https://openalex.org/T11918","display_name":"Forecasting Techniques and Applications","score":0.33660000562667847,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11918","display_name":"Forecasting Techniques and Applications","score":0.33660000562667847,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.3260999917984009,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.15610000491142273,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8007000088691711},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5995000004768372},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5939000248908997},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.5544999837875366},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4740999937057495},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43369999527931213},{"id":"https://openalex.org/keywords/database-normalization","display_name":"Database normalization","score":0.40689998865127563},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.3750999867916107},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.3749000132083893}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8007000088691711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6708999872207642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6556000113487244},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5995000004768372},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5939000248908997},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5514000058174133},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43369999527931213},{"id":"https://openalex.org/C162984825","wikidata":"https://www.wikidata.org/wiki/Q339072","display_name":"Database normalization","level":3,"score":0.40689998865127563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.32829999923706055},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C122282355","wikidata":"https://www.wikidata.org/wiki/Q7246855","display_name":"Probabilistic forecasting","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C74883015","wikidata":"https://www.wikidata.org/wiki/Q290467","display_name":"Autoregressive\u2013moving-average model","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2410.03935","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.03935","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":"article-journal"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2410.03935","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.03935","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":"article-journal"},"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":{"Despite":[0],"their":[1,232],"popularity,":[2],"deep":[3,130,162,228],"neural":[4],"networks":[5],"(DNNs)":[6],"applied":[7,184],"to":[8,14,123,185,245],"time":[9,80],"series":[10,81],"forecasting":[11,64,84,188,211,223,229],"often":[12],"fail":[13,66],"beat":[15],"simpler":[16],"statistical":[17,159],"models.":[18],"One":[19],"of":[20,24,44,53,89,108,128,134,157,170,237],"the":[21,29,40,45,50,87,112,125,129,135,141,145,155,168,171,220],"main":[22],"causes":[23],"this":[25,57],"suboptimal":[26],"performance":[27,169,233],"is":[28,137,179],"data":[30,47,127],"non-stationarity":[31],"present":[32],"in":[33,39,67,149,173,234],"many":[34],"processes.":[35],"In":[36,56],"particular,":[37],"changes":[38],"mean":[41,113],"and":[42,83,96,114,161,181,213],"variance":[43,115],"input":[46,126],"can":[48,182],"disrupt":[49],"predictive":[51],"capability":[52],"a":[54,75,90,97,105,150],"DNN.":[55],"paper,":[58],"we":[59,195],"first":[60,196],"show":[61,226],"how":[62],"DNN":[63,136,187,210],"models":[65,109,212,230],"simple":[68],"non-stationary":[69,174],"settings.":[70,175],"We":[71,204],"then":[72,205],"introduce":[73],"GAS-Norm,":[74],"novel":[76],"methodology":[77],"for":[78],"adaptive":[79,165],"normalization":[82,166,202,247],"based":[85],"on":[86,216],"combination":[88],"Generalized":[91],"Autoregressive":[92],"Score":[93],"(GAS)":[94],"model":[95,172],"Deep":[98],"Neural":[99],"Network.":[100],"The":[101,132,164,176],"GAS":[102,146],"approach":[103,152,178],"encompasses":[104],"score-driven":[106],"family":[107],"that":[110,153,227],"estimate":[111],"at":[116],"each":[117],"new":[118],"observation,":[119],"providing":[120],"updated":[121],"statistics":[122,142],"normalize":[124],"model.":[131,189],"output":[133],"eventually":[138],"denormalized":[139],"using":[140],"forecasted":[143],"by":[144],"model,":[147],"resulting":[148],"hybrid":[151],"leverages":[154],"strengths":[156],"both":[158],"modeling":[160],"learning.":[163],"improves":[167],"proposed":[177],"model-agnostic":[180],"be":[183],"any":[186],"To":[190],"empirically":[191],"validate":[192],"our":[193],"proposal,":[194],"compare":[197],"GAS-Norm":[198,243],"with":[199,208,242],"other":[200,246],"state-of-the-art":[201,209],"methods.":[203,248],"combine":[206],"it":[207],"test":[214],"them":[215],"real-world":[217],"datasets":[218],"from":[219],"Monash":[221],"open-access":[222],"repository.":[224],"Results":[225],"improve":[231],"21":[235],"out":[236],"25":[238],"settings":[239],"when":[240],"combined":[241],"compared":[244]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}