{"id":"https://openalex.org/W2970857099","doi":"https://doi.org/10.48550/arxiv.1909.05062","title":"Logarithmic Regret for Online Control","display_name":"Logarithmic Regret for Online Control","publication_year":2019,"publication_date":"2019-09-11","ids":{"openalex":"https://openalex.org/W2970857099","doi":"https://doi.org/10.48550/arxiv.1909.05062","mag":"2970857099"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1909.05062","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.05062","pdf_url":"https://arxiv.org/pdf/1909.05062","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/1909.05062","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007875487","display_name":"Naman Agarwal","orcid":"https://orcid.org/0000-0003-0320-0238","observed_orcids":["https://orcid.org/0000-0003-0320-0238"]},"institutions":[{"id":"https://openalex.org/I4210128969","display_name":"Alphabet (United States)","ror":"https://ror.org/02e9yx751","country_code":"US","type":"company","lineage":["https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Agarwal, Naman","raw_affiliation_strings":["Google AI Princeton","Alphabet Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google AI Princeton","institution_ids":[]},{"raw_affiliation_string":"Alphabet Inc","institution_ids":["https://openalex.org/I4210128969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024431603","display_name":"Elad Hazan","orcid":"https://orcid.org/0000-0002-1566-3216","observed_orcids":["https://orcid.org/0000-0002-1566-3216"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hazan, Elad","raw_affiliation_strings":["Department of Computer Science , Princeton University","Google AI Princeton","Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Princeton University","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Google AI Princeton","institution_ids":[]},{"raw_affiliation_string":"Computer Science","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101783963","display_name":"Karan Singh","orcid":"https://orcid.org/0000-0002-4831-7045","observed_orcids":["https://orcid.org/0000-0002-4831-7045"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Singh, Karan","raw_affiliation_strings":["Department of Computer Science , Princeton University","Google AI Princeton","Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Princeton University","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Google AI Princeton","institution_ids":[]},{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"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":73,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"10175","last_page":"10184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9940999746322632,"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":0.9940999746322632,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.003800000064074993,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/online-control","display_name":"online control","score":0.8629999756813049},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.8399999737739563},{"id":"https://openalex.org/keywords/logarithmic-regret","display_name":"logarithmic regret","score":0.8569999933242798},{"id":"https://openalex.org/keywords/linear-dynamical-systems","display_name":"linear dynamical systems","score":0.9739999771118164},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.9679999947547913},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"linear quadratic regulator","score":0.9990000128746033},{"id":"https://openalex.org/keywords/online-gradient-descent","display_name":"online gradient descent","score":0.9480000138282776}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9268811941146851},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6937662363052368},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.5804607272148132},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5354257822036743},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.494158536195755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48270463943481445},{"id":"https://openalex.org/C114275822","wikidata":"https://www.wikidata.org/wiki/Q621512","display_name":"Linear dynamical system","level":3,"score":0.4448530375957489},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43739259243011475},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.42713463306427},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.4166232645511627},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.408956378698349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39667901396751404},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.210389643907547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13444474339485168},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12781402468681335},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07727974653244019},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1909.05062","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.05062","pdf_url":"https://arxiv.org/pdf/1909.05062","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.1909.05062","doi":"https://doi.org/10.48550/arxiv.1909.05062","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.05062","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:2970857099","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/9207-logarithmic-regret-for-online-control.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.05062","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.05062","pdf_url":"https://arxiv.org/pdf/1909.05062","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/G3726267011","display_name":"AF: Large: Collaborative Research: Nonconvex Methods and Models for Learning: Toward Algorithms with Provable and Interpretable Guarantees","funder_award_id":"1704860","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970857099.pdf","grobid_xml":"https://content.openalex.org/works/W2970857099.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W53582479","https://openalex.org/W1570963478","https://openalex.org/W1586251222","https://openalex.org/W2077723394","https://openalex.org/W2101379030","https://openalex.org/W2151951067","https://openalex.org/W2188714131","https://openalex.org/W2513180554","https://openalex.org/W2765506414","https://openalex.org/W2785631679","https://openalex.org/W2786709902","https://openalex.org/W2787080146","https://openalex.org/W2804656147","https://openalex.org/W2850875954","https://openalex.org/W2886474253","https://openalex.org/W2915638893","https://openalex.org/W2963043564"],"related_works":["https://openalex.org/W3008658911","https://openalex.org/W4226099433","https://openalex.org/W7133199367","https://openalex.org/W2971091362","https://openalex.org/W2996025956","https://openalex.org/W3042160831","https://openalex.org/W3137534975","https://openalex.org/W4330336851","https://openalex.org/W2995725691","https://openalex.org/W4221147150"],"abstract_inverted_index":{"We":[0,59],"study":[1],"optimal":[2,63],"regret":[3,48,64,77],"bounds":[4],"for":[5],"control":[6],"in":[7,65],"linear":[8,39],"dynamical":[9],"systems":[10],"under":[11],"adversarially":[12],"changing":[13],"strongly":[14],"convex":[15],"cost":[16],"functions,":[17],"given":[18],"the":[19,34,38,44,56,62],"knowledge":[20],"of":[21,43],"transition":[22],"dynamics.":[23],"This":[24,76],"includes":[25],"several":[26],"well":[27],"studied":[28],"and":[29,37,90],"fundamental":[30],"frameworks":[31],"such":[32],"as":[33,51,73],"Kalman":[35],"filter":[36],"quadratic":[40],"regulator.":[41],"State":[42],"art":[45],"methods":[46],"achieve":[47],"which":[49],"scales":[50],"$O(\\sqrt{T})$,":[52],"where":[53],"$T$":[54],"is":[55,79],"time":[57],"horizon.":[58],"show":[60],"that":[61],"this":[66],"setting":[67],"can":[68],"be":[69],"significantly":[70],"smaller,":[71],"scaling":[72],"$O(\\text{poly}(\\log":[74],"T))$.":[75],"bound":[78],"achieved":[80],"by":[81],"two":[82],"different":[83],"efficient":[84],"iterative":[85],"methods,":[86],"online":[87,91],"gradient":[88],"descent":[89],"natural":[92],"gradient.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-09-05T00:00:00"}