{"id":"https://openalex.org/W7140169439","doi":"https://doi.org/10.48550/arxiv.2603.21375","title":"Constrained Online Convex Optimization with Memory and Predictions","display_name":"Constrained Online Convex Optimization with Memory and Predictions","publication_year":2026,"publication_date":"2026-03-22","ids":{"openalex":"https://openalex.org/W7140169439","doi":"https://doi.org/10.48550/arxiv.2603.21375"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.21375","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21375","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.21375","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Abdullah, Mohammed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdullah, Mohammed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Iosifidis, George","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iosifidis, George","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Elayoubi, Salah Eddine","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elayoubi, Salah Eddine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Chahed, Tijani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chahed, Tijani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.9444000124931335,"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":0.9444000124931335,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.020999999716877937,"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/T12288","display_name":"Optimization and Search Problems","score":0.006399999838322401,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/sublinear-function","display_name":"Sublinear function","score":0.789900004863739},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.6772000193595886},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.5734999775886536},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.5020999908447266},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.48899999260902405},{"id":"https://openalex.org/keywords/online-algorithm","display_name":"Online algorithm","score":0.4699000120162964}],"concepts":[{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.789900004863739},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6772000193595886},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6574000120162964},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.5734999775886536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5604000091552734},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.5020999908447266},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.4699000120162964},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C2989514635","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization problem","level":3,"score":0.3901999890804291},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.373199999332428},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29899999499320984},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2669999897480011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.21375","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21375","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.21375","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21375","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7166578769683838,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"study":[1],"Constrained":[2],"Online":[3],"Convex":[4],"Optimization":[5],"with":[6,37,54,78,118,160],"Memory":[7],"(COCO-M),":[8],"where":[9],"both":[10,77],"the":[11,14,26,31,46,62,113,143],"loss":[12,84],"and":[13,40,52,69,79,85,100,105,121,151,154],"constraints":[15],"depend":[16],"on":[17],"a":[18,156],"finite":[19],"window":[20],"of":[21,48,82],"past":[22],"decisions":[23],"made":[24],"by":[25],"learner.":[27],"This":[28],"setting":[29],"extends":[30],"previously":[32],"studied":[33],"unconstrained":[34],"online":[35,116,148],"optimization":[36,150],"memory":[38],"framework":[39],"captures":[41],"practical":[42],"problems":[43],"such":[44],"as":[45,115,129],"control":[47],"constrained":[49,147],"dynamical":[50],"systems":[51],"scheduling":[53],"reconfiguration":[55],"budgets.":[56],"For":[57],"this":[58],"problem,":[59],"we":[60,90,111],"propose":[61],"first":[63],"algorithms":[64],"that":[65,96],"achieve":[66],"sublinear":[67,70,98],"regret":[68,99],"cumulative":[71],"constraint":[72,86,101],"violation":[73],"under":[74],"time-varying":[75],"constraints,":[76],"without":[80],"predictions":[81,108,137],"future":[83],"functions.":[87],"Without":[88],"predictions,":[89],"introduce":[91],"an":[92,123],"adaptive":[93],"penalty":[94],"approach":[95],"guarantees":[97],"violation.":[102],"When":[103],"short-horizon":[104],"potentially":[106],"unreliable":[107],"are":[109,138],"available,":[110],"reinterpret":[112],"problem":[114],"learning":[117,158],"delayed":[119],"feedback":[120],"design":[122],"optimistic":[124],"algorithm":[125],"whose":[126],"performance":[127],"improves":[128],"prediction":[130],"accuracy":[131],"improves,":[132],"while":[133],"remaining":[134],"robust":[135],"when":[136],"inaccurate.":[139],"Our":[140],"results":[141],"bridge":[142],"gap":[144],"between":[145],"classical":[146],"convex":[149],"memory-dependent":[152],"settings,":[153],"provide":[155],"versatile":[157],"toolbox":[159],"diverse":[161],"applications.":[162]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-25T00:00:00"}