{"id":"https://openalex.org/W2963318627","doi":"https://doi.org/10.48550/arxiv.1708.04781","title":"Racing Thompson: an Efficient Algorithm for Thompson Sampling with Non-conjugate Priors","display_name":"Racing Thompson: an Efficient Algorithm for Thompson Sampling with Non-conjugate Priors","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2963318627","doi":"https://doi.org/10.48550/arxiv.1708.04781","mag":"2963318627"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1708.04781","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.04781","pdf_url":"https://arxiv.org/pdf/1708.04781","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1708.04781","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070094794","display_name":"Yichi Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Yichi","raw_affiliation_strings":["Department of Electronic Engineering , Tsinghua University , Beijing , 100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering , Tsinghua University , Beijing , 100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100606995","display_name":"Jun Zhu","orcid":"https://orcid.org/0000-0002-6254-2388","observed_orcids":["https://orcid.org/0000-0002-6254-2388"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Jun","raw_affiliation_strings":["Department of Computer Science & Technology , TNList Lab , Tsinghua University , Beijing , 100084","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Technology , TNList Lab , Tsinghua University , Beijing , 100084","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026923345","display_name":"Jingwei Zhuo","orcid":"https://orcid.org/0000-0001-8135-1061","observed_orcids":["https://orcid.org/0000-0001-8135-1061"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo, Jingwei","raw_affiliation_strings":["Department of Electronic Engineering , Tsinghua University , Beijing , 100084","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering , Tsinghua University , Beijing , 100084","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6000","last_page":"6008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.0,"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/thompson-sampling","display_name":"Thompson sampling","score":0.9990000128746033},{"id":"https://openalex.org/keywords/multi-armed-bandits","display_name":"multi-armed bandits","score":0.8859999775886536},{"id":"https://openalex.org/keywords/non-conjugate-priors","display_name":"non-conjugate priors","score":0.9990000128746033},{"id":"https://openalex.org/keywords/best-arm-identification","display_name":"best arm identification","score":0.8479999899864197},{"id":"https://openalex.org/keywords/posterior-sampling","display_name":"posterior sampling","score":0.45500001311302185},{"id":"https://openalex.org/keywords/optimization-reformulation","display_name":"optimization reformulation","score":0.5899999737739563}],"concepts":[{"id":"https://openalex.org/C26004113","wikidata":"https://www.wikidata.org/wiki/Q3711784","display_name":"Conjugate prior","level":4,"score":0.7855952978134155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6227342486381531},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6078018546104431},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.5917612314224243},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5536473989486694},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5455074906349182},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4314527213573456},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3903394341468811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3662784695625305},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2746341824531555},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.07317781448364258},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1708.04781","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.04781","pdf_url":"https://arxiv.org/pdf/1708.04781","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1708.04781","doi":"https://doi.org/10.48550/arxiv.1708.04781","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1708.04781","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"},{"id":"mag:2963318627","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v80/zhou18e/zhou18e.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1708.04781","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.04781","pdf_url":"https://arxiv.org/pdf/1708.04781","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1919465925","display_name":null,"funder_award_id":"61621136008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2197472058","display_name":null,"funder_award_id":"2013CB329403","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G368795326","display_name":null,"funder_award_id":"61620106010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7373123958","display_name":null,"funder_award_id":"2013CB329403","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963318627.pdf","grobid_xml":"https://content.openalex.org/works/W2963318627.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W95577512","https://openalex.org/W1506859583","https://openalex.org/W1585839838","https://openalex.org/W1598420512","https://openalex.org/W1880262756","https://openalex.org/W1911551976","https://openalex.org/W2039522160","https://openalex.org/W2049934117","https://openalex.org/W2104397175","https://openalex.org/W2108738385","https://openalex.org/W2158125716","https://openalex.org/W2168810201","https://openalex.org/W2283967462","https://openalex.org/W2294604761","https://openalex.org/W2296701362","https://openalex.org/W2464045740"],"related_works":["https://openalex.org/W3022268766","https://openalex.org/W4360764555","https://openalex.org/W2116720812","https://openalex.org/W4206886348","https://openalex.org/W2110632090","https://openalex.org/W1600255059","https://openalex.org/W2789027376","https://openalex.org/W4416113505","https://openalex.org/W4323572015","https://openalex.org/W4393147325"],"abstract_inverted_index":{"Thompson":[0,15,53,81],"sampling":[1,16,54,82],"has":[2],"impressive":[3],"empirical":[4],"performance":[5],"for":[6,14,19,52],"many":[7],"multi-armed":[8],"bandit":[9],"problems.":[10],"But":[11],"current":[12],"algorithms":[13,27],"only":[17,56],"work":[18],"the":[20,31,39,72,88,106],"case":[21],"of":[22,97],"conjugate":[23],"priors":[24],"since":[25],"these":[26],"require":[28],"to":[29,58,104],"infer":[30],"posterior,":[32],"which":[33,55],"is":[34,41,68,74,103],"often":[35],"computationally":[36],"intractable":[37],"when":[38,71],"prior":[40,73],"not":[42],"conjugate.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,79,93,112],"propose":[48],"a":[49,62,95],"novel":[50],"algorithm":[51,67],"requires":[57],"draw":[59],"samples":[60],"from":[61],"tractable":[63],"distribution,":[64],"so":[65],"our":[66,101],"efficient":[69],"even":[70],"non-conjugate.":[75],"To":[76],"do":[77],"this,":[78],"reformulate":[80],"as":[83],"an":[84],"optimization":[85],"problem":[86],"via":[87],"Gumbel-Max":[89],"trick.":[90],"After":[91],"that":[92],"construct":[94],"set":[96],"random":[98],"variables":[99],"and":[100],"goal":[102],"identify":[105],"one":[107],"with":[108,115],"highest":[109],"mean.":[110],"Finally,":[111],"solve":[113],"it":[114],"techniques":[116],"in":[117],"best":[118],"arm":[119],"identification.":[120]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2019-07-30T00:00:00"}