{"id":"https://openalex.org/W4289655432","doi":"https://doi.org/10.1109/isit50566.2022.9834474","title":"Tighter Expected Generalization Error Bounds via Convexity of Information Measures","display_name":"Tighter Expected Generalization Error Bounds via Convexity of Information Measures","publication_year":2022,"publication_date":"2022-06-26","ids":{"openalex":"https://openalex.org/W4289655432","doi":"https://doi.org/10.1109/isit50566.2022.9834474"},"language":"en","primary_location":{"id":"doi:10.1109/isit50566.2022.9834474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834474","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5010622937","display_name":"Gholamali Aminian","orcid":"https://orcid.org/0000-0002-4761-0151"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Gholamali Aminian","raw_affiliation_strings":["University College London"],"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007990317","display_name":"Yuheng Bu","orcid":"https://orcid.org/0000-0002-3479-4553"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuheng Bu","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066172831","display_name":"Gregory W. Wornell","orcid":"https://orcid.org/0000-0001-9166-4758"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory W. Wornell","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044634366","display_name":"Miguel R. D. Rodrigues","orcid":"https://orcid.org/0000-0002-8908-847X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Miguel R. D. Rodrigues","raw_affiliation_strings":["University College London"],"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010622937"],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":3.0949,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.94991243,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2481","last_page":"2486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/generalization","display_name":"Generalization","score":0.8781248331069946},{"id":"https://openalex.org/keywords/convexity","display_name":"Convexity","score":0.8085948824882507},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.7681396007537842},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5601062774658203},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.5525927543640137},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5388922095298767},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5258498787879944},{"id":"https://openalex.org/keywords/total-variation","display_name":"Total variation","score":0.4928731918334961},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.4912232756614685},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47766053676605225},{"id":"https://openalex.org/keywords/distance-measures","display_name":"Distance measures","score":0.47073233127593994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4426169693470001},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4327854812145233},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.4267627000808716},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37670934200286865},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37410467863082886},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3726893663406372},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2883152365684509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2517441511154175},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12265920639038086},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.0728955864906311}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8781248331069946},{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.8085948824882507},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.7681396007537842},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5601062774658203},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.5525927543640137},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5388922095298767},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5258498787879944},{"id":"https://openalex.org/C62100291","wikidata":"https://www.wikidata.org/wiki/Q1936288","display_name":"Total variation","level":2,"score":0.4928731918334961},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.4912232756614685},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47766053676605225},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.47073233127593994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4426169693470001},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4327854812145233},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.4267627000808716},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37670934200286865},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37410467863082886},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3726893663406372},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2883152365684509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2517441511154175},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12265920639038086},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0728955864906311},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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":"doi:10.1109/isit50566.2022.9834474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit50566.2022.9834474","pdf_url":null,"source":{"id":"https://openalex.org/S4363604560","display_name":"2022 IEEE International Symposium on Information Theory (ISIT)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1628829797","https://openalex.org/W1892947258","https://openalex.org/W1907483012","https://openalex.org/W2146950091","https://openalex.org/W2149298154","https://openalex.org/W2294642219","https://openalex.org/W2617539226","https://openalex.org/W2910572885","https://openalex.org/W2910589063","https://openalex.org/W2976533594","https://openalex.org/W2979452771","https://openalex.org/W2997949714","https://openalex.org/W3019669224","https://openalex.org/W3081982129","https://openalex.org/W3100231902","https://openalex.org/W3106002857","https://openalex.org/W3117521716","https://openalex.org/W3123190877","https://openalex.org/W3126302662","https://openalex.org/W3170524081","https://openalex.org/W3196434967","https://openalex.org/W3202333714","https://openalex.org/W3213800969","https://openalex.org/W3216201070","https://openalex.org/W4206043711","https://openalex.org/W4233762729","https://openalex.org/W4251333191","https://openalex.org/W4287371499","https://openalex.org/W4293774175","https://openalex.org/W4300167521","https://openalex.org/W6738074204","https://openalex.org/W6751754507","https://openalex.org/W6772932235","https://openalex.org/W6775928558","https://openalex.org/W6782591231","https://openalex.org/W6784595131","https://openalex.org/W6804346497","https://openalex.org/W7034108470"],"related_works":["https://openalex.org/W1970837389","https://openalex.org/W1520369951","https://openalex.org/W2205933074","https://openalex.org/W1765927794","https://openalex.org/W1657774708","https://openalex.org/W4226293580","https://openalex.org/W250432818","https://openalex.org/W4298345395","https://openalex.org/W4221165658","https://openalex.org/W4289655432"],"abstract_inverted_index":{"Generalization":[0],"error":[1,16,36,104],"bounds":[2,18,38,67],"are":[3,44,77],"essential":[4],"to":[5,58,79,96],"understanding":[6],"machine":[7],"learning":[8],"algorithms.":[9],"This":[10],"paper":[11],"presents":[12],"novel":[13],"expected":[14],"generalization":[15,35,103],"upper":[17,37],"based":[19,39,85],"on":[20,40,86],"the":[21,26,59,62,65,90,98,101],"average":[22],"joint":[23],"distribution":[24],"between":[25],"output":[27],"hypothesis":[28],"and":[29,54,73],"each":[30],"input":[31],"training":[32],"sample.":[33],"Multiple":[34],"different":[41],"information":[42,63],"measures":[43],"provided,":[45],"including":[46],"Wasserstein":[47,71],"distance,":[48,51],"total":[49,74],"variation":[50,75],"KL":[52],"divergence,":[53],"Jensen-Shannon":[55],"divergence.":[56],"Due":[57],"convexity":[60],"of":[61,70,100],"measures,":[64],"proposed":[66,102],"in":[68,89],"terms":[69],"distance":[72,76],"shown":[78],"be":[80],"tighter":[81],"than":[82],"their":[83],"counterparts":[84],"individual":[87],"samples":[88],"literature.":[91],"An":[92],"example":[93],"is":[94],"provided":[95],"demonstrate":[97],"tightness":[99],"bounds.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}