{"id":"https://openalex.org/W2811175972","doi":"https://doi.org/10.1145/3209978.3210068","title":"Reducing Variance in Gradient Bandit Algorithm using Antithetic Variates Method","display_name":"Reducing Variance in Gradient Bandit Algorithm using Antithetic Variates Method","publication_year":2018,"publication_date":"2018-06-27","ids":{"openalex":"https://openalex.org/W2811175972","doi":"https://doi.org/10.1145/3209978.3210068","mag":"2811175972"},"language":"en","primary_location":{"id":"doi:10.1145/3209978.3210068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209978.3210068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091157798","display_name":"Sihao Yu","orcid":"https://orcid.org/0000-0001-9658-727X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sihao Yu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020766468","display_name":"Jun Xu","orcid":"https://orcid.org/0000-0001-7170-111X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijng, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijng, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616866","display_name":"Yanyan Lan","orcid":"https://orcid.org/0000-0002-7811-3262"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Lan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088621320","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-9509-8674"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"885","last_page":"888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9994000196456909,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9988999962806702,"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/variance-reduction","display_name":"Variance reduction","score":0.8902222514152527},{"id":"https://openalex.org/keywords/control-variates","display_name":"Control variates","score":0.8890937566757202},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5930740237236023},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5624945163726807},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.5001528263092041},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.494279146194458},{"id":"https://openalex.org/keywords/delta-method","display_name":"Delta method","score":0.46110373735427856},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4480849802494049},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4433683454990387},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43838247656822205},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.42920249700546265},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4185214638710022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38248467445373535},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3630640506744385},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.2562657594680786},{"id":"https://openalex.org/keywords/hybrid-monte-carlo","display_name":"Hybrid Monte Carlo","score":0.15278339385986328},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.09063506126403809}],"concepts":[{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.8902222514152527},{"id":"https://openalex.org/C121683094","wikidata":"https://www.wikidata.org/wiki/Q3554721","display_name":"Control variates","level":5,"score":0.8890937566757202},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5930740237236023},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5624945163726807},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.5001528263092041},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.494279146194458},{"id":"https://openalex.org/C971699","wikidata":"https://www.wikidata.org/wiki/Q1132714","display_name":"Delta method","level":3,"score":0.46110373735427856},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4480849802494049},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4433683454990387},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43838247656822205},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.42920249700546265},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4185214638710022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38248467445373535},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3630640506744385},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2562657594680786},{"id":"https://openalex.org/C13153151","wikidata":"https://www.wikidata.org/wiki/Q1639846","display_name":"Hybrid Monte Carlo","level":4,"score":0.15278339385986328},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.09063506126403809},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3209978.3210068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3209978.3210068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2050505997","display_name":null,"funder_award_id":"61425016, 61472401, 61722211, 20180290","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W202801672","https://openalex.org/W2028145673","https://openalex.org/W2051130367","https://openalex.org/W2051203581","https://openalex.org/W2054259774","https://openalex.org/W2108682071","https://openalex.org/W2118309135","https://openalex.org/W2119717200","https://openalex.org/W2126559945","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2171677813","https://openalex.org/W2566089760","https://openalex.org/W3103182070","https://openalex.org/W3141232563","https://openalex.org/W4299828299"],"related_works":["https://openalex.org/W2057407087","https://openalex.org/W160467666","https://openalex.org/W2387727280","https://openalex.org/W2168027844","https://openalex.org/W2313927419","https://openalex.org/W4238545978","https://openalex.org/W2035518786","https://openalex.org/W2372826038","https://openalex.org/W363903320","https://openalex.org/W4362599072"],"abstract_inverted_index":{"Policy":[0],"gradient,":[1,54],"which":[2,164],"makes":[3],"use":[4],"of":[5,14,35,41,83,90,151,162,170,177],"Monte":[6,68],"Carlo":[7],"method":[8,51,78,104,115],"to":[9,70,110],"get":[10],"an":[11,200],"unbiased":[12,201],"estimation":[13,84],"the":[15,33,36,39,57,81,88,91,96,101,112,121,139,152,181,186,191],"parameter":[16],"gradients,":[17,172],"has":[18],"been":[19],"widely":[20],"used":[21,66],"in":[22,28,67,168],"reinforcement":[23],"learning.":[24],"One":[25,73],"key":[26],"issue":[27,97],"policy":[29,43,53,71,118,130],"gradient":[30,44,119,131,140,150,188],"is":[31,79,141,155,165],"reducing":[32],"variance":[34,49,63,106,203],"estimation.":[37,205],"From":[38],"viewpoint":[40],"statistics,":[42],"with":[45,75,116],"baseline,":[46],"a":[47,61,128,160,175,210],"successful":[48],"reduction":[50,64],"for":[52,105,120],"directly":[55],"applies":[56],"control":[58,76,92],"variates":[59,77,103,114],"method,":[60],"traditional":[62,117],"technique":[65],"Carlo,":[69],"gradient.":[72],"problem":[74],"that":[80,197,215],"quality":[82],"heavily":[85],"depends":[86],"on":[87,190,209],"choice":[89],"variates.":[93],"To":[94],"address":[95],"and":[98,183,202],"inspired":[99],"by":[100],"antithetic":[102,113,178],"reduction,":[107],"we":[108,126],"propose":[109],"combine":[111],"multi-armed":[122,211],"bandit":[123,212],"problem.":[124],"Furthermore,":[125],"achieve":[127,218],"new":[129],"algorithm":[132],"called":[133],"Antithetic-Arm":[134],"Bandit":[135],"(AAB).":[136],"In":[137],"AAB,":[138],"estimated":[142,156,171],"through":[143],"coordinate":[144],"ascent":[145],"where":[146],"at":[147],"each":[148],"iteration":[149],"target":[153,187],"arm":[154],"through:":[157],"1)":[158],"constructing":[159],"sequence":[161],"arms":[163,179],"approximately":[166],"monotonic":[167],"terms":[169],"2)":[173],"sampling":[174],"pair":[176],"over":[180],"sequence,":[182],"3)":[184],"re-estimating":[185],"based":[189,208],"sampled":[192],"pair.":[193],"Theoretical":[194],"analysis":[195],"proved":[196],"AAB":[198,216],"achieved":[199],"reduced":[204],"Experimental":[206],"results":[207],"task":[213],"showed":[214],"can":[217],"state-of-the-art":[219],"performances.":[220]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}