{"id":"https://openalex.org/W2795414739","doi":"https://doi.org/10.1109/isit.2018.8437679","title":"The Role of the Information Bottleneck in Representation Learning","display_name":"The Role of the Information Bottleneck in Representation Learning","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2795414739","doi":"https://doi.org/10.1109/isit.2018.8437679","mag":"2795414739"},"language":"en","primary_location":{"id":"doi:10.1109/isit.2018.8437679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2018.8437679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5052132831","display_name":"Mat\u00edas Vera","orcid":"https://orcid.org/0000-0001-9180-7595"},"institutions":[{"id":"https://openalex.org/I24354313","display_name":"University of Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]},{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"funder","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":true,"raw_author_name":"Matias Vera","raw_affiliation_strings":["Universidad de Buenos Aires (UBA), Facultad de Ingenieria, Buenos Aires, Argentina","CONICET - Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas [Buenos Aires] (Avda. Rivadavia 1917 - CP C1033AAJ - Cdad. de Buenos Aires - Argentina)"],"affiliations":[{"raw_affiliation_string":"Universidad de Buenos Aires (UBA), Facultad de Ingenieria, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I24354313"]},{"raw_affiliation_string":"CONICET - Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas [Buenos Aires] (Avda. Rivadavia 1917 - CP C1033AAJ - Cdad. de Buenos Aires - Argentina)","institution_ids":["https://openalex.org/I151201029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071189599","display_name":"Pablo Piantanida","orcid":"https://orcid.org/0000-0002-8717-2117"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210097418","display_name":"Laboratoire des signaux et syst\u00e8mes","ror":"https://ror.org/00skw9v43","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210097418","https://openalex.org/I4210107720"]},{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pablo Piantanida","raw_affiliation_strings":["CentraleSupelec-CNRS-Universite Paris-Sud, Laboratoire des Signaux et Systemes (L2S), Gif-sur-Yvette, France","L2S - Laboratoire des signaux et syst\u00e8mes (Plateau de Moulon 3 rue Joliot Curie 91192 GIF SUR YVETTE CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"CentraleSupelec-CNRS-Universite Paris-Sud, Laboratoire des Signaux et Systemes (L2S), Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I4210107720","https://openalex.org/I4210097418","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"L2S - Laboratoire des signaux et syst\u00e8mes (Plateau de Moulon 3 rue Joliot Curie 91192 GIF SUR YVETTE CEDEX - France)","institution_ids":["https://openalex.org/I4210097418"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035529329","display_name":"Leonardo Rey Vega","orcid":"https://orcid.org/0000-0002-5578-0521"},"institutions":[{"id":"https://openalex.org/I24354313","display_name":"University of Buenos Aires","ror":"https://ror.org/0081fs513","country_code":"AR","type":"education","lineage":["https://openalex.org/I24354313"]},{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"funder","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Leonardo Rey Vega","raw_affiliation_strings":["Facultad de Ingenieria UBA and CSC-CONICET, Buenos Aires, Argentina","CONICET - Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas [Buenos Aires] (Avda. Rivadavia 1917 - CP C1033AAJ - Cdad. de Buenos Aires - Argentina)"],"affiliations":[{"raw_affiliation_string":"Facultad de Ingenieria UBA and CSC-CONICET, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I24354313"]},{"raw_affiliation_string":"CONICET - Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas [Buenos Aires] (Avda. Rivadavia 1917 - CP C1033AAJ - Cdad. de Buenos Aires - Argentina)","institution_ids":["https://openalex.org/I151201029"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052132831"],"corresponding_institution_ids":["https://openalex.org/I151201029","https://openalex.org/I24354313"],"apc_list":null,"apc_paid":null,"fwci":3.2153,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93449546,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1580","last_page":"1584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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":0.9994000196456909,"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":0.9991000294685364,"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":0.8176268339157104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6600075960159302},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6348639130592346},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5734714865684509},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5197900533676147},{"id":"https://openalex.org/keywords/empirical-risk-minimization","display_name":"Empirical risk minimization","score":0.5061671137809753},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5039445757865906},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4840030372142792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45910337567329407},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4354058504104614},{"id":"https://openalex.org/keywords/information-theory","display_name":"Information theory","score":0.4316139221191406},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4271399974822998},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4229607880115509},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4206002950668335},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41062772274017334},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23055851459503174},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.18181639909744263}],"concepts":[{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.8176268339157104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6600075960159302},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6348639130592346},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5734714865684509},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5197900533676147},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.5061671137809753},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5039445757865906},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4840030372142792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45910337567329407},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4354058504104614},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.4316139221191406},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4271399974822998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4229607880115509},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4206002950668335},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41062772274017334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23055851459503174},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.18181639909744263},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isit.2018.8437679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2018.8437679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01756003v1","is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-01756003","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Symposium on Information Theory (ISIT 2018), Jun 2018, Vail, United States. ⟨10.1109/isit.2018.8437679⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W135467536","https://openalex.org/W1686946872","https://openalex.org/W1959608418","https://openalex.org/W1973631422","https://openalex.org/W2014902932","https://openalex.org/W2095705004","https://openalex.org/W2095734615","https://openalex.org/W2123469175","https://openalex.org/W2163922914","https://openalex.org/W2527691228","https://openalex.org/W2555129178","https://openalex.org/W2557579533","https://openalex.org/W2593634001","https://openalex.org/W2617539226","https://openalex.org/W2622255292","https://openalex.org/W2809994596","https://openalex.org/W2919115771","https://openalex.org/W2950011704","https://openalex.org/W2963862692","https://openalex.org/W2979452771","https://openalex.org/W2979454998","https://openalex.org/W3137695714","https://openalex.org/W4236966694","https://openalex.org/W4293469690","https://openalex.org/W4297749952","https://openalex.org/W6637108112","https://openalex.org/W6640963894","https://openalex.org/W6674330103","https://openalex.org/W6763485134"],"related_works":["https://openalex.org/W2622284819","https://openalex.org/W1504394672","https://openalex.org/W3089381707","https://openalex.org/W3034190530","https://openalex.org/W2741297526","https://openalex.org/W4295728955","https://openalex.org/W2070945723","https://openalex.org/W3129794609","https://openalex.org/W2949033103","https://openalex.org/W2304083841"],"abstract_inverted_index":{"A":[0],"grand":[1],"challenge":[2],"in":[3,137],"representation":[4],"learning":[5],"is":[6,38,112],"the":[7,14,35,54,60,64,84,90,104,110,116,123,133,148],"development":[8],"of":[9,18,56,63,70],"computational":[10],"algorithms":[11],"that":[12,50,95],"learn":[13],"different":[15],"explanatory":[16],"factors":[17],"variation":[19],"behind":[20],"high-dimensional":[21],"data.":[22,45],"Encoder":[23],"models":[24],"are":[25,107],"usually":[26],"determined":[27],"to":[28,39,42,83,89,114,122,131,146],"optimize":[29],"performance":[30],"on":[31],"training":[32],"data":[33],"when":[34,96],"real":[36],"objective":[37,119],"generalize":[40],"well":[41],"other":[43],"(unseen)":[44],"Although":[46],"numerical":[47],"evidence":[48],"suggests":[49],"noise":[51],"injection":[52],"at":[53],"level":[55],"representations":[57],"might":[58],"improve":[59],"generalization":[61,86,149],"ability":[62],"resulting":[65],"encoders,":[66],"an":[67,80],"information-theoretic":[68],"justification":[69],"this":[71,76,97,143],"principle":[72],"remains":[73],"elusive.":[74],"In":[75],"work,":[77],"we":[78],"derive":[79],"upper":[81],"bound":[82,98],"so-called":[85],"gap":[87],"corresponding":[88],"cross-entropy":[91],"loss":[92],"and":[93,103],"show":[94],"times":[99],"a":[100],"suitable":[101],"multiplier":[102],"empirical":[105,124],"risk":[106],"minimized":[108],"jointly,":[109],"problem":[111],"equivalent":[113],"optimizing":[115],"Information":[117],"Bottleneck":[118],"with":[120],"respect":[121],"data-distribution.":[125],"We":[126],"specialize":[127],"our":[128],"general":[129],"conclusions":[130],"analyze":[132],"dropout":[134],"regularization":[135],"method":[136],"deep":[138],"neural":[139],"networks,":[140],"explaining":[141],"how":[142],"regularizer":[144],"helps":[145],"decrease":[147],"gap.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}