{"id":"https://openalex.org/W3011680985","doi":"https://doi.org/10.48550/arxiv.2003.08485","title":"Self-Supervised Contextual Bandits in Computer Vision","display_name":"Self-Supervised Contextual Bandits in Computer Vision","publication_year":2020,"publication_date":"2020-03-18","ids":{"openalex":"https://openalex.org/W3011680985","doi":"https://doi.org/10.48550/arxiv.2003.08485","mag":"3011680985"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2003.08485","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.08485","pdf_url":"https://arxiv.org/pdf/2003.08485","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/2003.08485","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035432690","display_name":"Aniket Anand Deshmukh","orcid":"https://orcid.org/0000-0002-7292-8436","observed_orcids":["https://orcid.org/0000-0002-7292-8436"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deshmukh, Aniket Anand","raw_affiliation_strings":["Microsoft Ads , Microsoft AI & Research","\u2020University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Ads , Microsoft AI & Research","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"\u2020University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046535830","display_name":"Abhimanu Kumar","orcid":"https://orcid.org/0000-0003-4529-7883","observed_orcids":["https://orcid.org/0000-0003-4529-7883"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kumar, Abhimanu","raw_affiliation_strings":["Microsoft Ads , Microsoft AI & Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Ads , Microsoft AI & Research","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014330481","display_name":"Levi Boyles","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boyles, Levi","raw_affiliation_strings":["Microsoft Ads , Microsoft AI & Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Ads , Microsoft AI & Research","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008748926","display_name":"Denis Xavier Charles","orcid":"https://orcid.org/0009-0003-7921-3673","observed_orcids":["https://orcid.org/0009-0003-7921-3673"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles, Denis","raw_affiliation_strings":["Microsoft Ads , Microsoft AI & Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Ads , Microsoft AI & Research","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079433953","display_name":"Eren Manavoglu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manavoglu, Eren","raw_affiliation_strings":["Microsoft Ads , Microsoft AI & Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Ads , Microsoft AI & Research","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086993787","display_name":"\u00dcr\u00fcn Do\u01e7an","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dogan, Urun","raw_affiliation_strings":["Microsoft Ads , Microsoft AI & Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Ads , Microsoft AI & Research","institution_ids":["https://openalex.org/I1290206253"]}]}],"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":true,"cited_by_count":4,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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":9.999999747378752e-05,"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/contextual-bandits","display_name":"contextual bandits","score":0.9959999918937683},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"multi-objective optimization","score":0.5509999990463257},{"id":"https://openalex.org/keywords/cumulative-reward","display_name":"cumulative reward","score":0.5559999942779541},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.40799999237060547},{"id":"https://openalex.org/keywords/computer-vision-applications","display_name":"computer vision applications","score":0.5400000214576721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.709854006767273},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6921536922454834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6607534289360046},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6296901106834412},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6120060682296753},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6095747947692871},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5093908905982971},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12096267938613892},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2003.08485","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.08485","pdf_url":"https://arxiv.org/pdf/2003.08485","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":"mag:3011680985","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.08485","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2003.08485","doi":"https://doi.org/10.48550/arxiv.2003.08485","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.08485","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.08485","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.08485","pdf_url":"https://arxiv.org/pdf/2003.08485","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3011680985.pdf","grobid_xml":"https://content.openalex.org/works/W3011680985.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W77456527","https://openalex.org/W1487320471","https://openalex.org/W1579652926","https://openalex.org/W1614298861","https://openalex.org/W2006386362","https://openalex.org/W2112796928","https://openalex.org/W2118858186","https://openalex.org/W2138909795","https://openalex.org/W2144796873","https://openalex.org/W2163605009","https://openalex.org/W2166253248","https://openalex.org/W2182000050","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2614839826","https://openalex.org/W2734936460","https://openalex.org/W2750384547","https://openalex.org/W2785325870","https://openalex.org/W2785917027","https://openalex.org/W2809446765","https://openalex.org/W2883725317","https://openalex.org/W2885550588","https://openalex.org/W2895171208","https://openalex.org/W2897337230","https://openalex.org/W2901116712","https://openalex.org/W2914913933","https://openalex.org/W2917551568","https://openalex.org/W2943527153","https://openalex.org/W2948199691","https://openalex.org/W2950996604","https://openalex.org/W2951665052","https://openalex.org/W2962818688","https://openalex.org/W2964211955","https://openalex.org/W2964330179","https://openalex.org/W3036475571","https://openalex.org/W3118608800","https://openalex.org/W4394639701"],"related_works":["https://openalex.org/W2769857323","https://openalex.org/W2403579798","https://openalex.org/W2907316685","https://openalex.org/W2816000491","https://openalex.org/W2948044166","https://openalex.org/W3173925177","https://openalex.org/W4313019879","https://openalex.org/W3102153725","https://openalex.org/W2785371506","https://openalex.org/W4288929080"],"abstract_inverted_index":{"Contextual":[0],"bandits":[1],"are":[2],"a":[3,24,45,57,108,139,148,153,166],"common":[4],"problem":[5,69],"faced":[6],"by":[7,67,83,146],"machine":[8],"learning":[9,43,60,161,200],"practitioners":[10],"in":[11,28,91,112,131,181,201],"domains":[12],"as":[13,15],"diverse":[14],"hypothesis":[16],"testing":[17],"to":[18,48,127,142],"product":[19],"recommendations.":[20],"There":[21],"have":[22,119],"been":[23],"lot":[25],"of":[26,40,122,129,135],"approaches":[27],"exploiting":[29],"rich":[30,50],"data":[31,51,106,130],"representations":[32,52],"for":[33,107,198],"contextual":[34,114,149,159],"bandit":[35,115,150,160],"problems":[36],"with":[37,152,162],"varying":[38],"degree":[39],"success.":[41],"Self-supervised":[42],"is":[44,65,81],"promising":[46],"approach":[47,141],"find":[49],"without":[53],"explicit":[54],"labels.":[55],"In":[56,95],"typical":[58],"self-supervised":[59],"scheme,":[61],"the":[62,68,78,84,96,104,113,120,132,188],"primary":[63],"task":[64,80],"defined":[66,82],"objective":[70,86,151],"(e.g.":[71,87],"clustering,":[72],"classification,":[73],"embedding":[74],"generation":[75],"etc.)":[76],"and":[77,194],"secondary":[79,109],"self-supervision":[85,163],"rotation":[88],"prediction,":[89],"words":[90],"neighborhood,":[92],"colorization,":[93],"etc.).":[94],"usual":[97],"self-supervision,":[98],"we":[99,117,164],"learn":[100],"implicit":[101,124],"labels":[102,125],"from":[103],"training":[105],"task.":[110],"However,":[111],"setting,":[116],"don't":[118],"advantage":[121],"getting":[123],"due":[126],"lack":[128],"initial":[133],"phase":[134],"learning.":[136],"We":[137,184],"provide":[138,185],"novel":[140],"tackle":[143],"this":[144],"issue":[145],"combining":[147],"self":[154],"supervision":[155],"objective.":[156],"By":[157],"augmenting":[158],"get":[165],"better":[167,199],"cumulative":[168,182],"reward.":[169,183],"Our":[170],"results":[171],"on":[172],"eight":[173],"popular":[174],"computer":[175],"vision":[176],"datasets":[177],"show":[178],"substantial":[179],"gains":[180],"cases":[186],"where":[187],"proposed":[189],"scheme":[190],"doesn't":[191],"perform":[192],"optimally":[193],"give":[195],"alternative":[196],"methods":[197],"these":[202],"cases.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-03-23T00:00:00"}