{"id":"https://openalex.org/W3011154666","doi":"https://doi.org/10.1109/cdc40024.2019.9029461","title":"Decision Variance in Risk-Averse Online Learning","display_name":"Decision Variance in Risk-Averse Online Learning","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3011154666","doi":"https://doi.org/10.1109/cdc40024.2019.9029461","mag":"3011154666"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9029461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","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/A5009337709","display_name":"Sattar Vakili","orcid":"https://orcid.org/0000-0001-7085-1191"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sattar Vakili","raw_affiliation_strings":["Prowler.io, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Prowler.io, Cambridge, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020971679","display_name":"Alexis Boukouvalas","orcid":"https://orcid.org/0000-0003-3306-3692"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexis Boukouvalas","raw_affiliation_strings":["Prowler.io, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Prowler.io, Cambridge, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013788255","display_name":"Qing Zhao","orcid":"https://orcid.org/0000-0002-9590-4285"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Zhao","raw_affiliation_strings":["School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009337709"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3961,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69484768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7","issue":null,"first_page":"2738","last_page":"2744"},"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":0.9876999855041504,"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/T10603","display_name":"Smart Grid Energy Management","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.9505859613418579},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.7681180238723755},{"id":"https://openalex.org/keywords/risk-measure","display_name":"Risk measure","score":0.5614351034164429},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.5053582787513733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4821721911430359},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.46684250235557556},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.46538060903549194},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.46274450421333313},{"id":"https://openalex.org/keywords/risk-seeking","display_name":"Risk-seeking","score":0.44791918992996216},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.44401097297668457},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.4434521496295929},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37360239028930664},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.36090776324272156},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35002121329307556},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2761920690536499},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.2559354603290558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2088029384613037},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1742061972618103},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.08356758952140808}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9505859613418579},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.7681180238723755},{"id":"https://openalex.org/C2781472820","wikidata":"https://www.wikidata.org/wiki/Q2154759","display_name":"Risk measure","level":3,"score":0.5614351034164429},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5053582787513733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4821721911430359},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.46684250235557556},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.46538060903549194},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.46274450421333313},{"id":"https://openalex.org/C2779871187","wikidata":"https://www.wikidata.org/wiki/Q4333856","display_name":"Risk-seeking","level":2,"score":0.44791918992996216},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.44401097297668457},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.4434521496295929},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37360239028930664},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.36090776324272156},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35002121329307556},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2761920690536499},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2559354603290558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2088029384613037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1742061972618103},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.08356758952140808},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc40024.2019.9029461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/fb97fdbd-0035-4caa-9af0-b09ec9b275c6","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/fb97fdbd-0035-4caa-9af0-b09ec9b275c6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Vakili, S, Boukouvalas, A & Zhao, Q 2019, Decision Variance in Risk-Averse Online Learning. in 2019 IEEE 58th Conference on Decision and Control, CDC 2019 : 11-13 December 2019, Nice, France., 9029461, Proceedings of the IEEE Conference on Decision and Control, vol. 2019-December, IEEE, New York, pp. 2738-2744, 58th IEEE Conference on Decision and Control, CDC 2019, Nice, France, 11/12/19. https://doi.org/10.1109/CDC40024.2019.9029461","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W41047420","https://openalex.org/W952196006","https://openalex.org/W1570963478","https://openalex.org/W1590642498","https://openalex.org/W1831477278","https://openalex.org/W1975779216","https://openalex.org/W1984332158","https://openalex.org/W2009551863","https://openalex.org/W2039522160","https://openalex.org/W2062464341","https://openalex.org/W2077902449","https://openalex.org/W2120041647","https://openalex.org/W2120745256","https://openalex.org/W2161421585","https://openalex.org/W2164831377","https://openalex.org/W2166134957","https://openalex.org/W2168405694","https://openalex.org/W2339981478","https://openalex.org/W2400588688","https://openalex.org/W2551004485","https://openalex.org/W2891090109","https://openalex.org/W2962748815","https://openalex.org/W6601719174","https://openalex.org/W6638613290","https://openalex.org/W6678178185","https://openalex.org/W6683625788","https://openalex.org/W6684171789","https://openalex.org/W6713208385","https://openalex.org/W6755133355","https://openalex.org/W6807091881"],"related_works":["https://openalex.org/W2947263763","https://openalex.org/W4288373430","https://openalex.org/W4287753704","https://openalex.org/W3036260055","https://openalex.org/W3158925485","https://openalex.org/W2996735312","https://openalex.org/W3123538089","https://openalex.org/W2150167453","https://openalex.org/W1565681001","https://openalex.org/W2081965795"],"abstract_inverted_index":{"Online":[0],"learning":[1,15,52],"has":[2],"traditionally":[3],"focused":[4],"on":[5,50],"the":[6,18,22,25,30,73,76,89,94,101,107,108,111,118,121,131,140],"expected":[7,122],"rewards.":[8],"In":[9,55],"this":[10,134],"paper,":[11],"a":[12,62,147],"risk-averse":[13,51,148],"online":[14],"problem":[16],"under":[17,120],"performance":[19,39,145],"measure":[20],"of":[21,24,40,133,139],"mean-variance":[23,128],"rewards":[26],"is":[27,44,53,58,69,81,104],"studied.":[28],"Both":[29],"bandit":[31],"and":[32,46,154],"full":[33],"information":[34],"settings":[35],"are":[36],"considered.":[37],"The":[38,137],"several":[41],"existing":[42],"policies":[43],"analyzed,":[45],"new":[47],"fundamental":[48],"limitations":[49],"established.":[54],"particular,":[56],"it":[57],"shown":[59],"that":[60],"although":[61],"logarithmic":[63],"distribution-dependent":[64],"regret":[65,80,119,144],"in":[66,93,110,117,143],"time":[67],"T":[68],"achievable":[70],"(similar":[71],"to":[72,88,126,130],"risk-neutral":[74,95,102],"problem),":[75],"worst-case":[77],"(i.e.":[78],"minimax)":[79],"lower":[82,91],"bounded":[83],"by":[84,106],"\u03a9(T)":[85],"(in":[86],"contrast":[87],"\u03a9(\u221aT)":[90],"bound":[92],"problem).":[96],"This":[97],"sharp":[98],"difference":[99],"from":[100],"counterpart":[103],"caused":[105],"variance":[109,142],"player's":[112,149],"decisions,":[113],"which,":[114],"while":[115],"absent":[116],"reward":[123],"criterion,":[124],"contributes":[125],"excess":[127],"due":[129],"non-linearity":[132],"risk":[135],"measure.":[136],"role":[138],"decision":[141],"reflects":[146],"desire":[150],"for":[151],"robust":[152],"decisions":[153],"outcomes.":[155]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}