{"id":"https://openalex.org/W4385764211","doi":"https://doi.org/10.24963/ijcai.2023/405","title":"Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized R\u00e9nyi's Entropy Perspective","display_name":"Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized R\u00e9nyi's Entropy Perspective","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764211","doi":"https://doi.org/10.24963/ijcai.2023/405"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/405","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/405","pdf_url":"https://www.ijcai.org/proceedings/2023/0405.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0405.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101454000","display_name":"Yuxin Dong","orcid":"https://orcid.org/0000-0002-0166-7590"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Dong","raw_affiliation_strings":["School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030762002","display_name":"Tieliang Gong","orcid":"https://orcid.org/0000-0002-3840-441X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieliang Gong","raw_affiliation_strings":["School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074996561","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0002-1724-8649"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Chen","raw_affiliation_strings":["College of Science, Huazhong Agriculture University, Wuhan 430070, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science, Huazhong Agriculture University, Wuhan 430070, China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100369793","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-0079-3106"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an 710049, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55095263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3642","last_page":"3650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":1.0,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":1.0,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9980000257492065,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.996999979019165,"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/mutual-information","display_name":"Mutual information","score":0.7004743814468384},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.563564658164978},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5371312499046326},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5179520845413208},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48050105571746826},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4692264497280121},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38526082038879395},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.36369168758392334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3350231647491455},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28414788842201233}],"concepts":[{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.7004743814468384},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.563564658164978},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5371312499046326},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5179520845413208},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48050105571746826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4692264497280121},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38526082038879395},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.36369168758392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3350231647491455},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28414788842201233},{"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/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":"doi:10.24963/ijcai.2023/405","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/405","pdf_url":"https://www.ijcai.org/proceedings/2023/0405.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/405","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/405","pdf_url":"https://www.ijcai.org/proceedings/2023/0405.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2845948881","display_name":null,"funder_award_id":"12071166","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4303215675","display_name":null,"funder_award_id":"62192781","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4803403878","display_name":null,"funder_award_id":"62106191","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6387986177","display_name":null,"funder_award_id":"61721002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6800035256","display_name":null,"funder_award_id":"309439","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"},{"id":"https://openalex.org/G88417457","display_name":null,"funder_award_id":"2021ZD0110700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"},{"id":"https://openalex.org/F4320330193","display_name":"Chinese Academy of Engineering","ror":"https://ror.org/00z3yke57"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764211.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1811750039","https://openalex.org/W2566079294","https://openalex.org/W2741952635","https://openalex.org/W2915008147","https://openalex.org/W2962702650","https://openalex.org/W2962783375","https://openalex.org/W2963236897","https://openalex.org/W2963433607","https://openalex.org/W2963664410","https://openalex.org/W2969998143","https://openalex.org/W3033314398","https://openalex.org/W3128680160","https://openalex.org/W3158947877","https://openalex.org/W3162572380","https://openalex.org/W3172760977","https://openalex.org/W3191734561","https://openalex.org/W3202669415","https://openalex.org/W3208382257","https://openalex.org/W3212345415","https://openalex.org/W4287343372","https://openalex.org/W4287758986","https://openalex.org/W4287990479","https://openalex.org/W4288028699","https://openalex.org/W4288623659"],"related_works":["https://openalex.org/W2036846997","https://openalex.org/W2112223184","https://openalex.org/W2347586617","https://openalex.org/W2161963661","https://openalex.org/W2125614474","https://openalex.org/W2115702840","https://openalex.org/W2295845123","https://openalex.org/W2358054814","https://openalex.org/W2090882960","https://openalex.org/W2889544313"],"abstract_inverted_index":{"Recently,":[0],"information-theoretic":[1],"analysis":[2,21],"has":[3],"become":[4],"a":[5,19,78],"popular":[6],"framework":[7,48],"for":[8,22,123],"understanding":[9],"the":[10,41,65,95,113,119,130,141,155,158,164,171],"generalization":[11,43,120],"behavior":[12],"of":[13,67,97,112,140,143,157],"deep":[14],"neural":[15],"networks.":[16],"It":[17,93],"allows":[18],"direct":[20],"stochastic":[23,159],"gradient":[24],"/":[25],"Langevin":[26],"descent":[27],"(SGD/SGLD)":[28],"learning":[29],"algorithms":[30],"without":[31],"strong":[32],"assumptions":[33],"such":[34],"as":[35],"Lipschitz":[36],"or":[37],"convexity":[38],"conditions.":[39],"However,":[40],"current":[42,172],"error":[44,121],"bounds":[45,59,122,152],"within":[46],"this":[47,73],"are":[49,60,167,179],"still":[50],"far":[51],"from":[52],"optimal,":[53],"while":[54,109],"substantial":[55],"improvements":[56],"on":[57,154],"these":[58],"quite":[61],"challenging":[62],"due":[63],"to":[64],"intractability":[66],"high-dimensional":[68],"information":[69,80,132],"quantities.":[70],"To":[71],"address":[72],"issue,":[74],"we":[75],"first":[76],"propose":[77],"novel":[79],"theoretical":[81,177],"measure:":[82],"kernelized":[83,126],"R\u00e9nyi's":[84,127],"entropy,":[85,128],"by":[86,182],"utilizing":[87],"operator":[88],"representation":[89],"in":[90],"Hilbert":[91],"space.":[92],"inherits":[94],"properties":[96],"Shannon's":[98],"entropy":[99],"and":[100,166],"can":[101,134],"be":[102,135],"effectively":[103],"calculated":[104],"via":[105],"simple":[106],"random":[107],"sampling,":[108],"remaining":[110],"independent":[111],"input":[114],"dimension.":[115],"We":[116,147],"then":[117],"establish":[118],"SGD/SGLD":[124],"under":[125],"where":[129],"mutual":[131],"quantities":[133],"directly":[136],"calculated,":[137],"enabling":[138],"evaluation":[139],"tightness":[142],"each":[144],"intermediate":[145],"step.":[146],"show":[148],"that":[149],"our":[150],"information-theoretical":[151],"depend":[153],"statistics":[156],"gradients":[160],"evaluated":[161],"along":[162],"with":[163],"iterates,":[165],"rigorously":[168],"tighter":[169],"than":[170],"state-of-the-art":[173],"(SOTA)":[174],"results.":[175],"The":[176],"findings":[178],"also":[180],"supported":[181],"large-scale":[183],"empirical":[184],"studies.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}