{"id":"https://openalex.org/W2968948394","doi":"https://doi.org/10.13016/m2b56d796","title":"STOCHASTIC OPTIMIZATION: APPROXIMATE BAYESIAN INFERENCE AND COMPLETE EXPECTED IMPROVEMENT","display_name":"STOCHASTIC OPTIMIZATION: APPROXIMATE BAYESIAN INFERENCE AND COMPLETE EXPECTED IMPROVEMENT","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2968948394","doi":"https://doi.org/10.13016/m2b56d796","mag":"2968948394"},"language":"en","primary_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/21150","is_oa":true,"landing_page_url":"https://doi.org/10.13016/M2B56D796","pdf_url":"http://hdl.handle.net/1903/21150","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Dissertation"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1903/21150","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100359144","display_name":"Ye Chen","orcid":"https://orcid.org/0009-0002-4011-593X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100359144"],"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.4011000096797943,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.4011000096797943,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.20559999346733093,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.08649999648332596,"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/inference","display_name":"Inference","score":0.6122494339942932},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5255050659179688},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.482796311378479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4338315427303314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37049025297164917},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.36835289001464844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33497536182403564}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6122494339942932},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5255050659179688},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.482796311378479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4338315427303314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37049025297164917},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.36835289001464844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33497536182403564}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:drum.lib.umd.edu:1903/21150","is_oa":true,"landing_page_url":"https://doi.org/10.13016/M2B56D796","pdf_url":"http://hdl.handle.net/1903/21150","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Dissertation"},{"id":"mag:2968948394","is_oa":false,"landing_page_url":"https://drum.lib.umd.edu/handle/1903/21150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"doi:10.13016/m2b56d796","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m2b56d796","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Collection"}],"best_oa_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/21150","is_oa":true,"landing_page_url":"https://doi.org/10.13016/M2B56D796","pdf_url":"http://hdl.handle.net/1903/21150","source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Dissertation"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2968948394.pdf","grobid_xml":"https://content.openalex.org/works/W2968948394.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2341361091","https://openalex.org/W2534389769","https://openalex.org/W3182756250","https://openalex.org/W2759207936","https://openalex.org/W2384166280","https://openalex.org/W2166851633","https://openalex.org/W2422118299","https://openalex.org/W2910365588","https://openalex.org/W2962851448","https://openalex.org/W2615941983","https://openalex.org/W2386385231","https://openalex.org/W3202349828","https://openalex.org/W3159088669","https://openalex.org/W2111628293","https://openalex.org/W1521104898","https://openalex.org/W2982671608","https://openalex.org/W66466293","https://openalex.org/W1970031206","https://openalex.org/W2055978935","https://openalex.org/W2617977705"],"abstract_inverted_index":{"Stochastic":[0],"optimization":[1],"includes":[2],"modeling,":[3],"computing":[4],"and":[5,37,73,152,165,213,248,253,331],"decision":[6],"making.":[7],"In":[8],"practice,":[9],"due":[10],"to":[11,35,88,92,217,277,342,344],"the":[12,65,105,108,166,203,219,231,238,246,262,280,290,294,310,345],"limitation":[13],"of":[14,51,68,104,111,149,168,192,205,210,226,237,265,283,298,309,325],"mathematical":[15,259],"tools":[16],"or":[17,29,80,137],"real":[18],"budget,":[19],"many":[20,50],"practical":[21,44,99,281],"solution":[22],"methods":[23,314],"are":[24,33],"designed":[25],"using":[26],"approximation":[27,194],"techniques":[28,96],"taking":[30],"forms":[31],"that":[32,307],"efficient":[34,129],"compute":[36],"update.":[38],"These":[39],"models":[40,72,142,229],"have":[41,143,285],"shown":[42],"their":[43,75,98],"benefits":[45,282],"in":[46,146,158,289,293],"different":[47],"backgrounds,":[48],"but":[49],"them":[52],"also":[53],"lack":[54],"rigorous":[55],"theoretical":[56],"support.":[57],"Through":[58],"interfacing":[59],"with":[60,196,334],"statistical":[61,130],"tools,":[62],"we":[63],"analyze":[64],"asymptotic":[66],"properties":[67],"two":[69],"important":[70],"Bayesian":[71,117,120,140,170,187,228],"show":[74],"validity":[76],"by":[77,184],"proving":[78],"consistency":[79,109,167,182,221],"other":[81],"limiting":[82],"results,":[83],"which":[84],"may":[85],"be":[86,340],"useful":[87],"algorithmic":[89,275],"scientists":[90],"seeking":[91],"leverage":[93,214],"these":[94],"computational":[95],"for":[97,126,132,223,245,261],"performance.":[100],"The":[101,234,251],"first":[102,220],"part":[103,236],"thesis":[106,239],"is":[107,122,256,272],"analysis":[110,216],"sequential":[112,133],"learning":[113,134,141],"algorithms":[114],"under":[115],"approximate":[116,169,186,227],"inference.":[118],"Approximate":[119],"inference":[121,188],"a":[123,147,174,180,190,206,224,241,257,273,322],"powerful":[124],"methodology":[125],"constructing":[127],"computationally":[128],"mechanisms":[131],"from":[135,230],"incomplete":[136],"censored":[138],"information.Approximate":[139],"proven":[144],"successful":[145],"variety":[148],"operations":[150],"research":[151],"business":[153],"problems;":[154],"however,":[155],"prior":[156],"work":[157],"this":[159,211,215,278],"area":[160],"has":[161,172],"been":[162,173,287],"primarily":[163],"computational,":[164],"estimators":[171],"largely":[175],"open":[176],"problem.":[177,250],"We":[178,201,320],"develop":[179],"new":[181],"theory":[183],"interpreting":[185],"as":[189,328],"form":[191],"stochastic":[193],"(SA)":[195],"an":[197],"additional":[198],"\u201cbias\u201d":[199],"term.":[200],"prove":[202,332],"convergence":[204,318],"general":[207],"SA":[208],"algorithm":[209,244],"form,":[212],"derive":[218],"proofs":[222],"suite":[225],"recent":[232],"literature.":[233],"second":[235],"proposes":[240],"budget":[242,348],"allocation":[243,349],"ranking":[247,252],"selection":[249,254],"problem":[255],"well-known":[258,312],"framework":[260],"formal":[263],"study":[264],"optimal":[266,317],"information":[267],"collection.":[268],"Expected":[269],"improvement":[270],"(EI)":[271],"leading":[274],"approach":[276],"problem;":[279],"EI":[284,326],"repeatedly":[286],"demonstrated":[288],"literature,":[291],"especially":[292],"widely":[295],"studied":[296],"setting":[297],"Gaussian":[299],"sampling":[300],"distributions.":[301],"However,":[302],"it":[303,338],"was":[304],"recently":[305],"proved":[306],"some":[308,335],"most":[311],"EI-type":[313],"achieve":[315],"sub-":[316],"rates.":[319],"investigate":[321],"recently-proposed":[323],"variant":[324],"(known":[327],"\u201ccomplete":[329],"EI\u201d)":[330],"that,":[333],"minor":[336],"modifications,":[337],"can":[339],"made":[341],"converge":[343],"rate-optimal":[346],"static":[347],"without":[350],"requiring":[351],"any":[352],"tuning.":[353]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}