{"id":"https://openalex.org/W1543752008","doi":null,"title":"Semi-supervised learning via generalized maximum entropy","display_name":"Semi-supervised learning via generalized maximum entropy","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1543752008","mag":"1543752008"},"language":"en","primary_location":{"id":"mag:1543752008","doi":null,"is_oa":false,"landing_page_url":"http://is.tuebingen.mpg.de/fileadmin/user_upload/files/publications/AIStats2010-Erkan_[0].pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419146","display_name":"International Conference on Artificial Intelligence and Statistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"International Conference on Artificial Intelligence and Statistics","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5001226970","display_name":"Yann LeCun","orcid":"https://orcid.org/0000-0002-1992-2684","observed_orcids":["https://orcid.org/0000-0002-1992-2684"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yann LeCun","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":null,"display_name":"Alper Nabi Erkan","orcid":"https://orcid.org/0000-0001-7138-1400","observed_orcids":["https://orcid.org/0000-0001-7138-1400"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alper Nabi Erkan","raw_affiliation_strings":["New York University"],"raw_orcid":"https://orcid.org/0000-0001-7138-1400","affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":1.139,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.73507301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"209","last_page":"216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9990000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9990000128746033,"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/T12535","display_name":"Machine Learning and Data Classification","score":9.999999747378752e-05,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/generalized-maximum-entropy","display_name":"generalized maximum entropy","score":0.9779999852180481},{"id":"https://openalex.org/keywords/unlabeled-data","display_name":"unlabeled data","score":0.8489999771118164},{"id":"https://openalex.org/keywords/similarity-constraint","display_name":"similarity constraint","score":0.9459999799728394},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"logistic regression","score":0.7210000157356262},{"id":"https://openalex.org/keywords/kernel-logistic-regression","display_name":"kernel logistic regression","score":0.9950000047683716},{"id":"https://openalex.org/keywords/conditional-random-fields","display_name":"conditional random fields","score":0.8859999775886536},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"structured prediction","score":0.9850000143051147},{"id":"https://openalex.org/keywords/multiclass-classification","display_name":"multi-class classification","score":0.6869999766349792},{"id":"https://openalex.org/keywords/data-geometry","display_name":"data geometry","score":0.42800000309944153},{"id":"https://openalex.org/keywords/potential-function","display_name":"potential function","score":0.4959999918937683},{"id":"https://openalex.org/keywords/discriminative-learning","display_name":"discriminative learning","score":0.49900001287460327}],"concepts":[{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5346929430961609},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5259064435958862},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5240559577941895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.498934268951416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4677702784538269},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45577386021614075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43749818205833435},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4132572412490845},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3709256649017334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35938215255737305},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:1543752008","doi":null,"is_oa":false,"landing_page_url":"http://is.tuebingen.mpg.de/fileadmin/user_upload/files/publications/AIStats2010-Erkan_[0].pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419146","display_name":"International Conference on Artificial Intelligence and Statistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"International Conference on Artificial Intelligence and Statistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W36398315","https://openalex.org/W92894758","https://openalex.org/W345014192","https://openalex.org/W1479807131","https://openalex.org/W1489844845","https://openalex.org/W1497443639","https://openalex.org/W1513874326","https://openalex.org/W1529196404","https://openalex.org/W1542491098","https://openalex.org/W1546961578","https://openalex.org/W1548714966","https://openalex.org/W1551944942","https://openalex.org/W1560724230","https://openalex.org/W1574862351","https://openalex.org/W1574877594","https://openalex.org/W1579838312","https://openalex.org/W1585529040","https://openalex.org/W1630959083","https://openalex.org/W1640100566","https://openalex.org/W1663973292","https://openalex.org/W1787054552","https://openalex.org/W1820657498","https://openalex.org/W1881594620","https://openalex.org/W1979945719","https://openalex.org/W1982032418","https://openalex.org/W1996903695","https://openalex.org/W2002806284","https://openalex.org/W2005073772","https://openalex.org/W2014566476","https://openalex.org/W2031823405","https://openalex.org/W2032558547","https://openalex.org/W2038721957","https://openalex.org/W2041376653","https://openalex.org/W2074045464","https://openalex.org/W2077261816","https://openalex.org/W2095758845","https://openalex.org/W2096175520","https://openalex.org/W2101902009","https://openalex.org/W2105180921","https://openalex.org/W2105842272","https://openalex.org/W2107640784","https://openalex.org/W2107968230","https://openalex.org/W2112796928","https://openalex.org/W2113592823","https://openalex.org/W2115511080","https://openalex.org/W2115933183","https://openalex.org/W2116556696","https://openalex.org/W2117729721","https://openalex.org/W2122457239","https://openalex.org/W2125838338","https://openalex.org/W2127230571","https://openalex.org/W2127816222","https://openalex.org/W2132146097","https://openalex.org/W2134134392","https://openalex.org/W2135484641","https://openalex.org/W2136504847","https://openalex.org/W2137116439","https://openalex.org/W2137515156","https://openalex.org/W2141416357","https://openalex.org/W2142114717","https://openalex.org/W2142165428","https://openalex.org/W2145494108","https://openalex.org/W2147880316","https://openalex.org/W2148029428","https://openalex.org/W2148603752","https://openalex.org/W2149950545","https://openalex.org/W2150969560","https://openalex.org/W2151689911","https://openalex.org/W2151716017","https://openalex.org/W2153838241","https://openalex.org/W2154462399","https://openalex.org/W2157094900","https://openalex.org/W2160842254","https://openalex.org/W2161391345","https://openalex.org/W2163306339","https://openalex.org/W2165874743","https://openalex.org/W2169241897","https://openalex.org/W2169336678","https://openalex.org/W2282336968","https://openalex.org/W2312997001","https://openalex.org/W2331182131","https://openalex.org/W2469994344","https://openalex.org/W2561879720","https://openalex.org/W2903158431","https://openalex.org/W3145128584","https://openalex.org/W3151142710","https://openalex.org/W4212863985","https://openalex.org/W4302155765"],"related_works":["https://openalex.org/W581843499","https://openalex.org/W1571236831","https://openalex.org/W2145494108","https://openalex.org/W4387968130","https://openalex.org/W7170401771","https://openalex.org/W2798470481","https://openalex.org/W7097694157","https://openalex.org/W2122371783","https://openalex.org/W2810594911","https://openalex.org/W2887960245"],"abstract_inverted_index":{"The":[0,260],"maximum":[1,103],"entropy":[2,25,51,104],"(MaxEnt)":[3],"framework":[4,97,168,369],"has":[5,113,303],"been":[6],"studied":[7],"extensively":[8],"in":[9,117,151,196,289,331,404,452,503],"the":[10,14,33,63,101,118,134,165,192,215,228,241,249,286,290,298,322,327,332,336,339,345,352,358,366,405,408,413,441,444,449,453,457,483,489,498,510],"supervised":[11,71],"setting.":[12],"Here,":[13],"goal":[15],"is":[16,98,108,262,448,480,492],"to":[17,42,132,145,157,169,191,297,320,418,427],"find":[18],"a":[19,67,109,171,207,218,221,304,466],"distribution":[20],"p":[21,43],"that":[22,32,112,212,253,265,400,479,523],"maximizes":[23],"an":[24],"function":[26,204,211,288],"while":[27],"enforcing":[28],"data":[29,64,125,129,188,229,319,353,398,421],"constraints":[30,235,295,325],"so":[31,130],"expected":[34],"values":[35],"of":[36,69,138,153,173,198,217,264,266,284,326,338,344,365,412,443,460,468,476,485],"some":[37],"(pre-defined)":[38],"features":[39],"with":[40,127],"respect":[41],"match":[44],"their":[45],"empirical":[46,342,394],"counterparts":[47],"approximately.":[48],"Using":[49],"different":[50,53,59,179],"measures,":[52],"model":[54,258,340],"spaces":[55],"for":[56,62,206,361,380,387,494],"p,":[57],"and":[58,82,136,273,307,341,376,383,410,435,471],"approximation":[60],"criteria":[61],"constraints,":[65],"yields":[66],"family":[68,172],"discriminative":[70],"learning":[72,106,454,470,478],"methods":[73],"(e.g.,":[74],"logistic":[75,374,378],"regression,":[76],"conditional":[77,371,384],"random":[78,385],"fields,":[79],"least":[80],"squares":[81],"boosting)":[83],"(Dudik":[84],"&":[85,89,93],"Schapire,":[86],"2006;":[87,91],"Friedlander":[88],"Gupta,":[90],"Altun":[92],"Smola,":[94],"2006).":[95],"This":[96],"known":[99],"as":[100,131,236,514],"generalized":[102,166,328,367],"framework.\r\nSemi-supervised":[105],"(SSL)":[107],"promising":[110],"field":[111],"increasingly":[114],"attracted":[115],"attention":[116],"last":[119],"decade.":[120],"SSL":[121,143,175,500],"algorithms":[122,144,176,501,513],"utilize":[123],"unlabeled":[124,187,318],"along":[126],"labeled":[128,445,486],"increase":[133],"accuracy":[135],"robustness":[137],"inference":[139],"algorithms.":[140,415],"However,":[141],"most":[142],"date":[146],"have":[147,256,506],"had":[148],"trade-offs,":[149],"e.g.,":[150],"terms":[152,197],"scalability":[154],"or":[155],"applicability":[156],"multi-categorical":[158],"data.":[159],"\r\nIn":[160],"this":[161,504],"thesis,":[162],"we":[163,232,247,292,356,423,463],"extend":[164],"MaxEnt":[167,194,250,300,329,368],"develop":[170],"novel":[174,499],"using":[177,348],"two":[178,428],"approaches:":[180],"(1)":[181],"Introducing":[182],"Similarity":[183],"Constraints":[184,312],"We":[185,316,334],"incorporate":[186,317],"via":[189],"modifications":[190],"primal":[193,299],"objective":[195],"additional":[199,237],"potential":[200,203],"functions.":[201],"A":[202,392],"stands":[205],"closed":[208],"proper":[209],"convex":[210],"can":[213,524],"take":[214],"form":[216],"constraint":[219],"and/or":[220],"penalty":[222],"representing":[223],"our":[224,294,349,425],"structural":[225],"assumptions":[226,350],"on":[227,240,313,351,370,396,482],"geometry.":[230],"Specifically,":[231],"impose":[233],"similarity":[234],"penalties":[238],"based":[239,432],"semi-supervised":[242,359,469,512],"smoothness":[243],"assumption":[244],",":[245],"i.e.,":[246],"restrict":[248],"problem":[251,301,330,490],"such":[252],"similar":[254,257],"samples":[255,447],"outputs.":[259],"motivation":[261],"reminiscent":[263],"Laplacian":[267],"SVM":[268],"(Sindhwani":[269],"et":[270,279],"al.,":[271,280],"2005)":[272],"manifold":[274],"transductive":[275],"neural":[276],"networks":[277],"(Karlen":[278],"2008),":[281],"however,":[282],"instead":[283],"regularizing":[285],"loss":[287,521],"dual":[291],"integrate":[293],"directly":[296],"which":[302],"more":[305],"straight-forward":[306],"natural":[308],"interpretation.":[309],"(2)":[310],"Augmenting":[311],"Model":[314],"Features":[315],"enhance":[321],"moment":[323],"matching":[324],"primal.":[333],"improve":[335],"estimates":[337],"expectations":[343],"feature":[346],"functions":[347,522],"geometry.\r\nIn":[354],"particular,":[355],"derive":[357],"formulations":[360],"three":[362],"specific":[363],"instances":[364],"distributions,":[372],"namely":[373],"regression":[375,379],"kernel":[377],"multi-class":[381,520],"problems,":[382,430],"fields":[386],"structured":[388],"output":[389],"prediction":[390],"problems.":[391],"thorough":[393],"evaluation":[395],"standard":[397],"sets":[399],"are":[401],"widely":[402],"used":[403],"literature":[406],"demonstrates":[407],"validity":[409],"competitiveness":[411],"proposed":[414,502],"In":[416],"addition":[417],"these":[419],"benchmark":[420],"sets,":[422],"apply":[424],"approach":[426],"real-life":[429],"vision":[431],"robot":[433],"grasping,":[434],"remote":[436],"sensing":[437],"image":[438],"classification":[439],"where":[440],"scarcity":[442,484],"training":[446],"main":[450],"bottleneck":[451],"process.":[455],"For":[456],"particular":[458],"case":[459],"grasp":[461],"learning,":[462,473],"also":[464],"propose":[465],"combination":[467],"active":[472],"another":[474],"sub-field":[475],"machine":[477],"focused":[481],"samples,":[487],"when":[488],"setup":[491],"suitable":[493],"incremental":[495],"labeling.\r\nTo":[496],"conclude,":[497],"thesis":[505],"numerous":[507],"advantages":[508],"over":[509],"existing":[511],"they":[515],"yield":[516],"convex,":[517],"scalable,":[518],"inherently":[519],"be":[525],"kernelized":[526],"naturally.":[527]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}