{"id":"https://openalex.org/W3214171157","doi":"https://doi.org/10.1109/mlsp52302.2021.9596544","title":"Beyond the Bias Variance Trade-Off: A Mutual Information Trade-Off in Deep Learning","display_name":"Beyond the Bias Variance Trade-Off: A Mutual Information Trade-Off in Deep Learning","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3214171157","doi":"https://doi.org/10.1109/mlsp52302.2021.9596544","mag":"3214171157"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp52302.2021.9596544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5018413478","display_name":"Xinjie Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinjie Lan","raw_affiliation_strings":["University of Delaware, Newark, DE, USA"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065767090","display_name":"Bin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Zhu","raw_affiliation_strings":["University of Delaware, Newark, DE, USA"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113690844","display_name":"Charles Boncelet","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Boncelet","raw_affiliation_strings":["University of Delaware, Newark, DE, USA"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036946701","display_name":"Kenneth E. Barner","orcid":"https://orcid.org/0000-0002-0936-7840"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth Barner","raw_affiliation_strings":["University of Delaware, Newark, DE, USA"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018413478"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56702143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9997000098228455,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9997000098228455,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"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/T10320","display_name":"Neural Networks and Applications","score":0.9983000159263611,"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/overfitting","display_name":"Overfitting","score":0.8751815557479858},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.8514653444290161},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.7126359939575195},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6685722470283508},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6620707511901855},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5621914863586426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5606948137283325},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5303611755371094},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5278947949409485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5180397629737854},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5101625919342041},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3854238986968994},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38078436255455017},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.321147620677948},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28210076689720154},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1663074791431427},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.092134028673172}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8751815557479858},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8514653444290161},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7126359939575195},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6685722470283508},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6620707511901855},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5621914863586426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5606948137283325},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5303611755371094},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5278947949409485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5180397629737854},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5101625919342041},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3854238986968994},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38078436255455017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.321147620677948},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28210076689720154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1663074791431427},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.092134028673172},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp52302.2021.9596544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1516193414","https://openalex.org/W1522301498","https://openalex.org/W2070902649","https://openalex.org/W2076118331","https://openalex.org/W2149298154","https://openalex.org/W2161914416","https://openalex.org/W2527691228","https://openalex.org/W2593634001","https://openalex.org/W2617539226","https://openalex.org/W2732724430","https://openalex.org/W2750384547","https://openalex.org/W2766196653","https://openalex.org/W2805159540","https://openalex.org/W2897025488","https://openalex.org/W2946006146","https://openalex.org/W2949759968","https://openalex.org/W2963518130","https://openalex.org/W2963650125","https://openalex.org/W2963716183","https://openalex.org/W2963739978","https://openalex.org/W2963862692","https://openalex.org/W2964034630","https://openalex.org/W2964121744","https://openalex.org/W3008906732","https://openalex.org/W3046489903","https://openalex.org/W4211192810","https://openalex.org/W4285719527","https://openalex.org/W4293774175","https://openalex.org/W4297749952","https://openalex.org/W4300167521","https://openalex.org/W4301881812","https://openalex.org/W4378767342","https://openalex.org/W6631190155","https://openalex.org/W6728598543","https://openalex.org/W6738074204","https://openalex.org/W6740483536","https://openalex.org/W6743688258","https://openalex.org/W6747679287","https://openalex.org/W6755053738","https://openalex.org/W6762796984","https://openalex.org/W6766511095","https://openalex.org/W6772932235","https://openalex.org/W6774375107"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W2922073769","https://openalex.org/W4378510483","https://openalex.org/W2490526372","https://openalex.org/W1770458422","https://openalex.org/W2786764570","https://openalex.org/W4309960894"],"abstract_inverted_index":{"The":[0],"classical":[1,58],"bias":[2,59],"variance":[3,60],"trade-off":[4,31,64],"cannot":[5],"accurately":[6,51,67],"explain":[7],"how":[8],"over-parameterized":[9,72],"Deep":[10],"Neural":[11],"Networks":[12],"(DNNs)":[13],"avoid":[14],"overfitting":[15],"and":[16,82],"achieve":[17],"good":[18],"generalization.":[19,40,83],"To":[20],"address":[21],"the":[22,34,53,57,62,69,77],"problem,":[23],"we":[24,43],"alternatively":[25],"derive":[26],"a":[27,45],"Mutual":[28],"Information":[29],"(MI)":[30],"based":[32],"on":[33],"recently":[35],"proposed":[36],"MI":[37,63],"explanation":[38],"for":[39,50],"In":[41],"addition,":[42],"propose":[44],"probabilistic":[46],"representation":[47],"of":[48,71],"DNNs":[49,73],"estimating":[52],"MI.":[54],"Compared":[55],"to":[56],"trade-off,":[61],"not":[65],"only":[66],"measures":[68],"generalization":[70],"but":[74],"also":[75],"formulates":[76],"relation":[78],"between":[79],"DNN":[80],"architecture":[81]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}