{"id":"https://openalex.org/W7151294539","doi":"https://doi.org/10.48550/arxiv.2604.03614","title":"Neural Global Optimization via Iterative Refinement from Noisy Samples","display_name":"Neural Global Optimization via Iterative Refinement from Noisy Samples","publication_year":2026,"publication_date":"2026-04-04","ids":{"openalex":"https://openalex.org/W7151294539","doi":"https://doi.org/10.48550/arxiv.2604.03614"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.03614","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03614","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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.03614","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088485831","display_name":"Qusay Muzaffar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muzaffar, Qusay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133128332","display_name":"David Levin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Levin, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073083818","display_name":"Michael Werman","orcid":"https://orcid.org/0000-0002-0665-967X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Werman, Michael","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.36010000109672546,"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":0.36010000109672546,"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":0.1914999932050705,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.09950000047683716,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/maxima-and-minima","display_name":"Maxima and minima","score":0.8414000272750854},{"id":"https://openalex.org/keywords/global-optimization","display_name":"Global optimization","score":0.7247999906539917},{"id":"https://openalex.org/keywords/spline","display_name":"Spline (mechanical)","score":0.4875999987125397},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4293000102043152},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.413100004196167},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4000000059604645},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.39649999141693115},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.3912999927997589}],"concepts":[{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.8414000272750854},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.7247999906539917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4966000020503998},{"id":"https://openalex.org/C10390562","wikidata":"https://www.wikidata.org/wiki/Q581809","display_name":"Spline (mechanical)","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4731000065803528},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4366999864578247},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38040000200271606},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3463999927043915},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3434999883174896},{"id":"https://openalex.org/C202286095","wikidata":"https://www.wikidata.org/wiki/Q579262","display_name":"Error function","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26080000400543213},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.03614","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03614","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"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.03614","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03614","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Global":[0],"optimization":[1,137,165],"of":[2,98,127,148],"black-box":[3],"functions":[4,82],"from":[5],"noisy":[6,57],"samples":[7,59],"is":[8],"a":[9,41,95,114],"fundamental":[10],"challenge":[11],"in":[12,124],"machine":[13],"learning":[14],"and":[15,60,155],"scientific":[16],"computing.":[17],"Traditional":[18],"methods":[19,34],"such":[20],"as":[21,65],"Bayesian":[22],"Optimization":[23],"often":[24],"converge":[25],"to":[26,47,107],"local":[27],"minima":[28,50,87,123],"on":[29,79,101],"multi-modal":[30,103],"functions,":[31,105],"while":[32],"gradient-free":[33],"require":[35],"many":[36],"function":[37,58,152],"evaluations.":[38],"We":[39],"present":[40],"novel":[42],"neural":[43],"approach":[44],"that":[45],"learns":[46],"find":[48],"global":[49,76,86,122,164],"through":[51],"iterative":[52,159],"refinement.":[53],"Our":[54,144],"model":[55,119],"takes":[56],"their":[61],"fitted":[62],"spline":[63,112,156],"representation":[64],"input,":[66],"then":[67],"iteratively":[68],"refines":[69],"an":[70],"initial":[71],"guess":[72],"toward":[73],"the":[74,111],"true":[75],"minimum.":[77],"Trained":[78],"randomly":[80],"generated":[81],"with":[83,130,158],"ground":[84],"truth":[85],"obtained":[88],"via":[89],"exhaustive":[90],"search,":[91],"our":[92],"method":[93],"achieves":[94],"mean":[96],"error":[97,131],"8.05":[99],"percent":[100,109,116,126],"challenging":[102],"test":[104,128],"compared":[106],"36.24":[108],"for":[110],"initialization,":[113],"28.18":[115],"improvement.":[117],"The":[118],"successfully":[120],"finds":[121],"72":[125],"cases":[129],"below":[132],"10":[133],"percent,":[134],"demonstrating":[135],"learned":[136],"principles":[138],"rather":[139],"than":[140],"mere":[141],"curve":[142],"fitting.":[143],"architecture":[145],"combines":[146],"encoding":[147],"multiple":[149,171],"modalities":[150],"including":[151],"values,":[153],"derivatives,":[154],"coefficients":[157],"position":[160],"updates,":[161],"enabling":[162],"robust":[163],"without":[166],"requiring":[167],"derivative":[168],"information":[169],"or":[170],"restarts.":[172]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-08T00:00:00"}