{"id":"https://openalex.org/W7095445767","doi":null,"title":"Proximal regularization for online and batch learning Chuong B.","display_name":"Proximal regularization for online and batch learning Chuong B.","publication_year":2010,"publication_date":"2010-03-20","ids":{"openalex":"https://openalex.org/W7095445767"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.215","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ai.stanford.edu/~chuongdo/papers/proximal_proofs.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5088551093","display_name":"Quoc Viet Le","orcid":"https://orcid.org/0000-0002-1087-2844","observed_orcids":["https://orcid.org/0000-0002-1087-2844"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Quoc V. Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5088551093"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50067172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9253000020980835,"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"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9253000020980835,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.06199999898672104,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0024999999441206455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/proximal-regularization","display_name":"proximal regularization","score":1.0},{"id":"https://openalex.org/keywords/regularization-parameter-selection","display_name":"regularization parameter selection","score":0.7580000162124634},{"id":"https://openalex.org/keywords/strong-convexity","display_name":"strong convexity","score":0.7509999871253967},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.8379999995231628},{"id":"https://openalex.org/keywords/batch-learning","display_name":"batch learning","score":0.8100000023841858},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.8230000138282776},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"logistic regression","score":0.8169999718666077},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"structured prediction","score":0.968999981880188},{"id":"https://openalex.org/keywords/conditional-random-fields","display_name":"conditional random fields","score":0.9919999837875366},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.972000002861023},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.5040000081062317},{"id":"https://openalex.org/keywords/pegasos","display_name":"Pegasos","score":0.7950000166893005},{"id":"https://openalex.org/keywords/bundle-method","display_name":"bundle method","score":0.9860000014305115}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.5412999987602234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5299000144004822},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49239999055862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44609999656677246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4410000145435333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4251999855041504},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38190001249313354},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3682999908924103},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.30090001225471497},{"id":"https://openalex.org/C79248915","wikidata":"https://www.wikidata.org/wiki/Q17086776","display_name":"Proximal gradient methods for learning","level":5,"score":0.28630000352859497},{"id":"https://openalex.org/C39891107","wikidata":"https://www.wikidata.org/wiki/Q5767098","display_name":"Hinge loss","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C2778134712","wikidata":"https://www.wikidata.org/wiki/Q1047307","display_name":"Bundle","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C141718189","wikidata":"https://www.wikidata.org/wiki/Q7309628","display_name":"Regularization perspectives on support vector machines","level":4,"score":0.26660001277923584},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.215","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ai.stanford.edu/~chuongdo/papers/proximal_proofs.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.5402368307113647,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2106129230","https://openalex.org/W4398224607","https://openalex.org/W58266356","https://openalex.org/W1691729031","https://openalex.org/W7100271330","https://openalex.org/W2341954556","https://openalex.org/W3127099038","https://openalex.org/W2589602506","https://openalex.org/W2164301055","https://openalex.org/W7099411789"],"abstract_inverted_index":{"Many":[0],"learning":[1,83,123,181],"algorithms":[2,49,76,146,164],"rely":[3],"on":[4,174],"the":[5,23,30,98,121,141,152,159],"curvature":[6,139],"(in":[7],"particular,":[8],"strong":[9],"convexity)":[10],"of":[11,25,81,101,128],"regularized":[12,53],"objective":[13,38],"functions":[14,39,106],"to":[15,136],"provide":[16],"good":[17],"theoretical":[18],"performance":[19,34],"guarantees.":[20],"In":[21,46],"practice,":[22],"choice":[24,100],"regularization":[26,102],"penalty":[27],"that":[28,63],"gives":[29],"best":[31],"testing":[32],"set":[33],"may":[35],"result":[36],"in":[37,68,105,117,151,158],"with":[40,107],"little":[41],"or":[42,59],"even":[43],"no":[44],"curvature.":[45,109],"these":[47],"cases,":[48],"designed":[50],"specifically":[51],"for":[52,77],"objectives":[54,133],"often":[55],"either":[56],"fail":[57],"completely":[58],"require":[60],"some":[61],"modification":[62],"involves":[64],"a":[65,79,112,126],"substantial":[66],"compromise":[67],"performance.":[69],"We":[70,110],"present":[71],"new":[72],"online":[73,153],"and":[74,93,155,171,176,179],"batch":[75,160],"training":[78],"variety":[80],"supervised":[82],"models":[84],"(such":[85],"as":[86],"SVMs,":[87],"logistic":[88],"regression,":[89],"structured":[90,180],"prediction":[91],"models,":[92],"CRFs)":[94],"under":[95],"conditions":[96],"where":[97],"optimal":[99],"parameter":[103],"results":[104],"low":[108,148],"employ":[111],"technique":[113],"called":[114],"proximal":[115],"regularization,":[116],"which":[118],"we":[119],"solve":[120],"original":[122,142],"problem":[124],"via":[125],"sequence":[127],"modified":[129],"optimization":[130],"tasks":[131],"whose":[132],"are":[134],"chosen":[135],"have":[137],"greater":[138],"than":[140],"problem.":[143],"Theoretically,":[144],"our":[145,163],"achieve":[147],"regret":[149],"bounds":[150],"setting":[154],"fast":[156],"convergence":[157],"setting.":[161],"Experimentally,":[162],"improve":[165],"upon":[166],"state-of-the-art":[167],"techniques,":[168],"including":[169],"Pegasos":[170],"bundle":[172],"methods,":[173],"medium":[175],"large-scale":[177],"SVM":[178],"tasks.":[182],"1.":[183]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-27T00:00:00"}