{"id":"https://openalex.org/W7135181778","doi":"https://doi.org/10.48550/arxiv.2603.11276","title":"RIE-Greedy: Regularization-Induced Exploration for Contextual Bandits","display_name":"RIE-Greedy: Regularization-Induced Exploration for Contextual Bandits","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135181778","doi":"https://doi.org/10.48550/arxiv.2603.11276"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.11276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11276","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2603.11276","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128952245","display_name":"Tong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Tong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129092678","display_name":"Thiago de Queiroz Casanova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Casanova, Thiago de Queiroz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101996440","display_name":"Eric M. Schwartz","orcid":"https://orcid.org/0000-0001-7747-1511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schwartz, Eric M.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128970934","display_name":"Victor Kostyuk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kostyuk, Victor","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129065646","display_name":"Dehan Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Dehan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128927948","display_name":"Joseph J. Williams","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Williams, Joseph J.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5128952245"],"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9344000220298767,"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":0.9344000220298767,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.00800000037997961,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.007799999788403511,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.720300018787384},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.6255000233650208},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.5875999927520752},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5755000114440918},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5458999872207642},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4683000147342682},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4535999894142151},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44609999656677246}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.720300018787384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.703000009059906},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.6255000233650208},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.5875999927520752},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5755000114440918},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5458999872207642},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.542900025844574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5329999923706055},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3971000015735626},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.3968000113964081},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.357699990272522},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.11276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11276","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.11276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11276","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"contextual":[1,165],"bandit":[2,121,166],"problems":[3],"with":[4,11],"complex":[5],"reward":[6],"models":[7],"are":[8,51],"often":[9],"tackled":[10],"iteratively":[12],"trained":[13],"models,":[14],"such":[15,137],"as":[16,31,82,138],"boosting":[17],"trees.":[18],"However,":[19],"it":[20],"is":[21,112],"difficult":[22],"to":[23,53,115,126,134],"directly":[24],"apply":[25],"simple":[26],"and":[27,55,123,140,161],"effective":[28,155],"exploration":[29,111,128],"strategies--such":[30],"Thompson":[32,103,116],"Sampling":[33,117],"or":[34,47],"UCB--on":[35],"top":[36],"of":[37,66,86],"those":[38],"black-box":[39],"estimators.":[40],"Existing":[41],"approaches":[42],"rely":[43],"on":[44],"sophisticated":[45],"assumptions":[46],"intractable":[48],"procedures":[49],"that":[50,73,92,108],"hard":[52],"verify":[54],"implement":[56],"in":[57,78,95,118,129],"practice.":[58],"In":[59],"this":[60,109],"work,":[61],"we":[62,90],"explore":[63],"the":[64,75,93,119],"use":[65],"an":[67,83],"exploration-free":[68],"(pure-greedy)":[69],"action":[70],"selection":[71],"strategy,":[72],"exploits":[74],"randomness":[76],"inherent":[77],"model":[79],"fitting":[80],"process":[81,99],"intrinsic":[84],"source":[85],"exploration.":[87,105],"More":[88],"specifically,":[89],"note":[91],"stochasticity":[94],"cross-validation":[96],"based":[97],"regularization":[98],"can":[100,153],"naturally":[101],"induce":[102,154],"Sampling-like":[104],"We":[106],"show":[107],"regularization-induced":[110],"theoretically":[113],"equivalent":[114],"two-armed":[120],"case":[122],"empirically":[124],"leads":[125],"reliable":[127],"large-scale":[130],"business":[131],"environments":[132],"compared":[133],"benchmark":[135],"methods":[136],"epsilon-greedy":[139],"other":[141],"state-of-the-art":[142],"approaches.":[143],"Overall,":[144],"our":[145],"work":[146],"reveals":[147],"how":[148],"regularized":[149],"estimator":[150],"training":[151],"itself":[152],"exploration,":[156],"offering":[157],"both":[158],"theoretical":[159],"insight":[160],"practical":[162],"guidance":[163],"for":[164],"design.":[167]},"counts_by_year":[],"updated_date":"2026-03-14T06:46:50.379900","created_date":"2026-03-14T00:00:00"}