{"id":"https://openalex.org/W7225010683","doi":"https://doi.org/10.5281/zenodo.23829509","title":"Lookahead Weight-Averaging Intervention Optimization (LWAIO): A Predictive Framework for Adaptive Weight-Averaging Selection During Model Training","display_name":"Lookahead Weight-Averaging Intervention Optimization (LWAIO): A Predictive Framework for Adaptive Weight-Averaging Selection During Model Training","publication_year":2026,"publication_date":"2026-10-31","ids":{"openalex":"https://openalex.org/W7225010683","doi":"https://doi.org/10.5281/zenodo.23829509"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23829509","doi":"https://doi.org/10.5281/zenodo.23829509","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829509","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23829509","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133561621","display_name":"Jincheng Zhang","orcid":"https://orcid.org/0009-0005-1860-0009","observed_orcids":["https://orcid.org/0009-0005-1860-0009"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Jincheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0005-1860-0009","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5133561621"],"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.4291999936103821,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.4291999936103821,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.41110000014305115,"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":0.10700000077486038,"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/weight-averaging","display_name":"weight averaging","score":0.9909999966621399},{"id":"https://openalex.org/keywords/parameter-averaging","display_name":"parameter averaging","score":0.47600001096725464},{"id":"https://openalex.org/keywords/exponentially-weighted-moving-average","display_name":"exponential moving average","score":0.8420000076293945},{"id":"https://openalex.org/keywords/stochastic-weight-averaging","display_name":"stochastic weight averaging","score":0.996999979019165},{"id":"https://openalex.org/keywords/intervention-selection","display_name":"intervention selection","score":0.5370000004768372},{"id":"https://openalex.org/keywords/predictive-validation","display_name":"predictive validation","score":0.5339999794960022},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8289999961853027},{"id":"https://openalex.org/keywords/model-stability","display_name":"model stability","score":0.39500001072883606},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.6119999885559082}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7681999802589417},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5364999771118164},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5343999862670898},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.513700008392334},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3840000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36820000410079956},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33869999647140503},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32659998536109924},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C3019719930","wikidata":"https://www.wikidata.org/wiki/Q3910099","display_name":"Predictive value","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23829509","doi":"https://doi.org/10.5281/zenodo.23829509","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829509","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.23829510","doi":"https://doi.org/10.5281/zenodo.23829510","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829510","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.5281/zenodo.23829509","doi":"https://doi.org/10.5281/zenodo.23829509","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829509","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4400141854","https://openalex.org/W4407632580","https://openalex.org/W7165941123","https://openalex.org/W4281684405","https://openalex.org/W4407359552","https://openalex.org/W7225018739","https://openalex.org/W3209362138","https://openalex.org/W4405029557","https://openalex.org/W4322503680","https://openalex.org/W2792287754"],"abstract_inverted_index":{"Weight":[0],"averaging":[1,23,27,36,201,218,248],"is":[2,38,213,287,312],"an":[3,50,107,195,333],"established":[4],"technique":[5],"for":[6,93,208,279,314],"stabilizing":[7],"model":[8,85,104,109],"parameters":[9,105],"and":[10,25,77,96,106,123,156,169,219,254,274,297,304,325],"potentially":[11],"improving":[12],"generalization.":[13],"Common":[14],"approaches":[15],"include":[16],"exponential":[17],"moving":[18],"average":[19],"(EMA),":[20],"stochastic":[21],"weight":[22,232],"(SWA),":[24],"uniform":[26,152],"over":[28],"selected":[29],"training":[30,76,95,180],"checkpoints.":[31],"However,":[32],"the":[33,65,81,84,102,139,165,178,190,200,261,298,326],"choice":[34],"of":[35,53,68,83,100,119,141,171,328],"strategy":[37],"often":[39],"determined":[40],"by":[41,49],"fixed":[42,113,144,247],"hyperparameters":[43],"or":[44,91,203,231],"conventional":[45,216,250],"practice":[46],"rather":[47],"than":[48],"explicit":[51],"prediction":[52,295],"its":[54],"future":[55,66,166],"validation":[56,167,302],"performance.":[57,308],"Lookahead":[58],"Weight-Averaging":[59],"Intervention":[60],"Optimization":[61],"(LWAIO)":[62],"investigates":[63],"whether":[64,187,238],"performance":[67],"alternative":[69,157],"parameter-averaging":[70],"strategies":[71],"can":[72,241],"be":[73,89],"estimated":[74],"during":[75],"used":[78],"to":[79,188,227,289],"guide":[80],"selection":[82,331],"representation":[86,207],"that":[87],"will":[88],"evaluated":[90],"retained":[92],"subsequent":[94],"final":[97,306],"deployment.":[98],"Instead":[99],"treating":[101],"current":[103,142,179,191],"averaged":[108,197],"as":[110],"mutually":[111],"exclusive":[112],"choices,":[114],"LWAIO":[115,223,281],"considers":[116,134],"a":[117,275],"set":[118],"candidate":[120,136,173,206,266],"weight-averaging":[121,330],"interventions":[122],"evaluates":[124],"their":[125],"potential":[126],"downstream":[127],"effects":[128],"through":[129],"predictive":[130,161,220,269,329],"validation.":[131],"The":[132,309],"framework":[133,311],"several":[135],"interventions,":[137],"including":[138],"use":[140],"parameters,":[143,192],"EMA":[145,148],"coefficients,":[146],"multiple":[147],"decay":[149],"rates,":[150],"finite-window":[151],"averaging,":[153,155],"cumulative":[154],"checkpoint-averaging":[158],"schedules.":[159],"A":[160,210],"evaluation":[162,240,270],"component":[163,184],"estimates":[164],"utility":[168],"stability":[170],"each":[172],"using":[174,194],"information":[175],"available":[176],"at":[177],"stage.":[181],"An":[182],"intervention-selection":[183],"then":[185],"determines":[186],"retain":[189],"continue":[193],"existing":[196],"model,":[198],"modify":[199],"configuration,":[202],"select":[204],"another":[205],"evaluation.":[209],"central":[211],"distinction":[212,299],"made":[214],"between":[215,300],"parameter":[217],"intervention":[221,267],"selection.":[222],"does":[224],"not":[225],"claim":[226],"introduce":[228],"EMA,":[229],"SWA,":[230],"averaging.":[233],"Its":[234],"research":[235,335],"question":[236],"concerns":[237],"prospective":[239],"provide":[242],"additional":[243],"decision":[244],"value":[245],"beyond":[246],"policies,":[249],"validation-based":[251],"checkpoint":[252],"selection,":[253],"inexpensive":[255],"adaptive":[256],"baselines.":[257],"This":[258],"paper":[259],"presents":[260],"conceptual":[262],"framework,":[263],"mathematical":[264],"formulation,":[265],"space,":[268],"mechanism,":[271],"experimental":[272,277,318],"hypotheses,":[273],"controlled":[276],"protocol":[278],"investigating":[280],"in":[282,322],"diffusion-model":[283],"training.":[284],"Particular":[285],"attention":[286],"given":[288],"matched":[290],"computational":[291],"budgets,":[292],"validation-data":[293],"separation,":[294],"uncertainty,":[296],"intermediate":[301],"improvements":[303],"independent":[305],"generation":[307],"proposed":[310],"intended":[313],"empirical":[315],"investigation.":[316],"No":[317],"results":[319],"are":[320],"claimed":[321],"this":[323],"paper,":[324],"effectiveness":[327],"remains":[332],"open":[334],"question.":[336]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-11-01T00:00:00"}