{"id":"https://openalex.org/W7150855914","doi":"https://doi.org/10.48550/arxiv.2604.02920","title":"Efficient Logistic Regression with Mixture of Sigmoids","display_name":"Efficient Logistic Regression with Mixture of Sigmoids","publication_year":2026,"publication_date":"2026-04-03","ids":{"openalex":"https://openalex.org/W7150855914","doi":"https://doi.org/10.48550/arxiv.2604.02920"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.02920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02920","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.02920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120599149","display_name":"Federico Di Gennaro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Gennaro, Federico","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076850079","display_name":"Saptarshi Chakraborty","orcid":"https://orcid.org/0000-0002-3668-637X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chakraborty, Saptarshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133044808","display_name":"Nikita Zhivotovskiy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhivotovskiy, Nikita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":0.9448999762535095,"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":0.9448999762535095,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.014600000344216824,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.006899999920278788,"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/regret","display_name":"Regret","score":0.7555000185966492},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.521399974822998},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.453900009393692},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.4311000108718872},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.3901999890804291},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.36230000853538513},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.32659998536109924},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.3179999887943268}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7597000002861023},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7555000185966492},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.49540001153945923},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3944999873638153},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38830000162124634},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.30630001425743103},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.26170000433921814}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.02920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02920","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.02920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02920","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,54],"paper":[1],"studies":[2],"the":[3,20,35,58,65,76,86,98,102,120,123,130,150,161],"Exponential":[4],"Weights":[5],"(EW)":[6],"algorithm":[7],"with":[8,47,129,160],"an":[9],"isotropic":[10],"Gaussian":[11,95,126],"prior":[12,62],"for":[13,26],"online":[14,179],"logistic":[15],"regression.":[16],"We":[17],"show":[18,167],"that":[19,143,168],"near-optimal":[21],"worst-case":[22,49],"regret":[23,140,151],"bound":[24],"$O(d\\log(Bn))$":[25],"EW,":[27],"established":[28],"by":[29,84],"Kakade":[30],"and":[31,156,175],"Ng":[32],"(2005)":[33],"against":[34],"best":[36],"linear":[37,80],"predictor":[38,103],"of":[39,61,117,122,154],"norm":[40],"at":[41],"most":[42],"$B$,":[43,85],"can":[44,170],"be":[45,171],"achieved":[46],"total":[48],"computational":[50],"complexity":[51,60],"$O(B^3":[52],"n^5)$.":[53],"substantially":[55],"improves":[56],"on":[57,113],"$O(B^{18}n^{37})$":[59],"work":[63],"achieving":[64],"same":[66],"guarantee":[67],"(Foster":[68],"et":[69],"al.,":[70],"2018).":[71],"Beyond":[72],"efficiency,":[73],"we":[74,137],"analyze":[75],"large-$B$":[77],"regime":[78],"under":[79],"separability:":[81],"after":[82],"rescaling":[83],"EW":[87,169],"posterior":[88],"converges":[89,104],"as":[90],"$B\\to\\infty$":[91],"to":[92,97,105],"a":[93,106,147],"standard":[94],"truncated":[96,125],"version":[99],"cone.":[100],"Accordingly,":[101],"solid-angle":[107],"vote":[108],"over":[109],"separating":[110],"directions":[111],"and,":[112],"every":[114],"fixed-margin":[115],"slice":[116],"this":[118,135],"cone,":[119],"mode":[121],"corresponding":[124],"is":[127],"aligned":[128],"hard-margin":[131],"SVM":[132],"direction.":[133],"Using":[134],"geometry,":[136],"derive":[138],"non-asymptotic":[139],"bounds":[141],"showing":[142],"once":[144],"$B$":[145,155],"exceeds":[146],"margin-dependent":[148],"threshold,":[149],"becomes":[152],"independent":[153],"grows":[157],"only":[158],"logarithmically":[159],"inverse":[162],"margin.":[163],"Overall,":[164],"our":[165],"results":[166],"both":[172],"computationally":[173],"tractable":[174],"geometrically":[176],"adaptive":[177],"in":[178],"classification.":[180]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-07T00:00:00"}