{"id":"https://openalex.org/W4285396586","doi":"https://doi.org/10.13097/archive-ouverte/unige:174561","title":"Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility","display_name":"Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility","publication_year":2022,"publication_date":"2022-07-11","ids":{"openalex":"https://openalex.org/W4285396586","doi":"https://doi.org/10.13097/archive-ouverte/unige:174561"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2207.04895","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.04895","pdf_url":"https://arxiv.org/pdf/2207.04895","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2207.04895","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034055082","display_name":"Behrooz Razeghi","orcid":"https://orcid.org/0000-0001-9568-4166"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Razeghi, Behrooz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5034055082"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9847000241279602,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9847000241279602,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9739999771118164,"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":0.9449999928474426,"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/information-bottleneck-method","display_name":"Information bottleneck method","score":0.8834379315376282},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6752806901931763},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6099328398704529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115379095077515},{"id":"https://openalex.org/keywords/information-theory","display_name":"Information theory","score":0.5024981498718262},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.48895156383514404},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46428006887435913},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4493449628353119},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.447912335395813},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42274224758148193},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31035423278808594},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.2789291739463806},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19600826501846313}],"concepts":[{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.8834379315376282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6752806901931763},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6099328398704529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115379095077515},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.5024981498718262},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.48895156383514404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46428006887435913},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4493449628353119},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.447912335395813},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42274224758148193},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31035423278808594},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.2789291739463806},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19600826501846313},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2207.04895","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.04895","pdf_url":"https://arxiv.org/pdf/2207.04895","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:unige.ch:aou:unige:174561","is_oa":true,"landing_page_url":"https://archive-ouverte.unige.ch/unige:174561","pdf_url":null,"source":{"id":"https://openalex.org/S4306402259","display_name":"Archive ouverte UNIGE (University of Geneva)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114457229","host_organization_name":"University of Geneva","host_organization_lineage":["https://openalex.org/I114457229"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Th\u00e8se"},{"id":"doi:10.48550/arxiv.2207.04895","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2207.04895","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.13097/archive-ouverte/unige:174561","is_oa":true,"landing_page_url":"https://doi.org/10.13097/archive-ouverte/unige:174561","pdf_url":null,"source":{"id":"https://openalex.org/S7407051284","display_name":"Uni Genf","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"thesis"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2207.04895","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.04895","pdf_url":"https://arxiv.org/pdf/2207.04895","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4285396586.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4281766347","https://openalex.org/W2987280934","https://openalex.org/W4241564561","https://openalex.org/W2070945723","https://openalex.org/W4324286871","https://openalex.org/W1551759367","https://openalex.org/W3120332801","https://openalex.org/W3167660944","https://openalex.org/W4301016710","https://openalex.org/W3177409857"],"abstract_inverted_index":{"Bottleneck":[0],"problems":[1,8,166],"are":[2,25],"an":[3,218],"important":[4],"class":[5],"of":[6,18,36,58,77,91,192,206,288],"optimization":[7,59,127],"that":[9,74,159,262],"have":[10],"recently":[11],"gained":[12],"increasing":[13],"attention":[14],"in":[15,28,45,112,217,270],"the":[16,78,82,92,103,113,120,134,160,178,193,207,214,241,254,263,276,281,285,312],"domain":[17],"machine":[19,32,290],"learning":[20,33,273,291],"and":[21,39,95,107,153,209,248,300,310],"information":[22,140,195,200],"theory.":[23],"They":[24],"widely":[26],"used":[27,111,269],"generative":[29,94,104,115,227,234],"models,":[30,85,97,106,228],"fair":[31,114,271],"algorithms,":[34],"design":[35],"privacy-assuring":[37],"mechanisms,":[38],"appear":[40],"as":[41,62,123,167,169,230,238,240],"information-theoretic":[42,83,172],"performance":[43],"bounds":[44],"various":[46],"multi-user":[47],"communication":[48],"problems.":[49],"In":[50],"this":[51],"work,":[52],"we":[53,176,202,221],"propose":[54],"a":[55,70,88,124,289,304],"general":[56],"family":[57],"problems,":[60,138,274],"termed":[61],"complexity-leakage-utility":[63],"bottleneck":[64,137,141,151],"(CLUB)":[65],"model,":[66],"which":[67],"(i)":[68],"provides":[69],"unified":[71,204],"theoretical":[72],"framework":[73],"generalizes":[75,163],"most":[76,170],"state-of-the-art":[79,226],"literature":[80],"for":[81],"privacy":[84,143,173],"(ii)":[86],"establishes":[87],"new":[89,100],"interpretation":[90],"popular":[93],"discriminative":[96],"(iii)":[98],"constructs":[99],"insights":[101],"to":[102,188,279,308],"compression":[105],"(iv)":[108],"can":[109,266],"be":[110,268],"models.":[116,174,212],"We":[117,129,157,259,293],"first":[118],"formulate":[119],"CLUB":[121,161,181,313],"model":[122,162,216,265],"complexity-constrained":[125],"privacy-utility":[126],"problem.":[128,258],"then":[130,222,260],"connect":[131,223],"it":[132,224],"with":[133,225,303],"closely":[135],"related":[136],"namely":[139],"(IB),":[142],"funnel":[144],"(PF),":[145],"deterministic":[146],"IB":[147],"(DIB),":[148],"conditional":[149,154],"entropy":[150],"(CEB),":[152],"PF":[155],"(CPF).":[156],"show":[158,261],"all":[164],"these":[165,199],"well":[168,239],"other":[171],"Then,":[175],"construct":[177],"deep":[179],"variational":[180,190,231],"(DVCLUB)":[182],"models":[183,252],"by":[184],"employing":[185],"neural":[186],"networks":[187,236],"parameterize":[189],"approximations":[191],"associated":[194],"quantities.":[196],"Building":[197],"upon":[198],"quantities,":[201],"present":[203],"objectives":[205],"supervised":[208],"unsupervised":[210,219],"DVCLUB":[211,215,264],"Leveraging":[213],"setup,":[220],"such":[229],"auto-encoders":[232],"(VAEs),":[233],"adversarial":[235,249],"(GANs),":[237],"Wasserstein":[242,245],"GAN":[243],"(WGAN),":[244],"auto-encoder":[246,250],"(WAE),":[247],"(AAE)":[251],"through":[253],"optimal":[255],"transport":[256],"(OT)":[257],"also":[267],"representation":[272],"where":[275],"goal":[277],"is":[278],"mitigate":[280],"undesired":[282],"bias":[283],"during":[284],"training":[286],"phase":[287],"model.":[292,314],"conduct":[294],"extensive":[295],"quantitative":[296],"experiments":[297],"on":[298],"colored-MNIST":[299],"CelebA":[301],"datasets,":[302],"public":[305],"implementation":[306],"available,":[307],"evaluate":[309],"analyze":[311]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}