{"id":"https://openalex.org/W2970812740","doi":"https://doi.org/10.1137/19m1236886","title":"Stop Memorizing: A Data-Dependent Regularization Framework for Intrinsic Pattern Learning","display_name":"Stop Memorizing: A Data-Dependent Regularization Framework for Intrinsic Pattern Learning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970812740","doi":"https://doi.org/10.1137/19m1236886","mag":"2970812740"},"language":"en","primary_location":{"id":"doi:10.1137/19m1236886","is_oa":true,"landing_page_url":"https://doi.org/10.1137/19m1236886","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/19M1236886","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://epubs.siam.org/doi/pdf/10.1137/19M1236886","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101589682","display_name":"Wei Zhu","orcid":"https://orcid.org/0000-0002-9181-5103"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wei Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101992408","display_name":"Qiang Qiu","orcid":"https://orcid.org/0000-0003-2610-3502"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Qiu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376439","display_name":"Bao Wang","orcid":"https://orcid.org/0000-0002-4848-4791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061472917","display_name":"Jianfeng Lu","orcid":"https://orcid.org/0000-0001-6255-5165"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianfeng Lu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025218580","display_name":"Guillermo Sapiro","orcid":"https://orcid.org/0000-0001-9190-6964"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillermo Sapiro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108565885","display_name":"Ingrid Daubechies","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ingrid Daubechies","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101589682"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3783,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59139154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":"3","first_page":"476","last_page":"496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"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/T12676","display_name":"Machine Learning and ELM","score":0.9973000288009644,"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/softmax-function","display_name":"Softmax function","score":0.6417953968048096},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.619184136390686},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5979962944984436},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5834054946899414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5338403582572937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5044761896133423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48817116022109985},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.4672280251979828},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.460345059633255},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45740818977355957},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.42891842126846313},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4205617308616638},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3769993782043457},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36632847785949707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3417798578739166},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.17633694410324097}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6417953968048096},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.619184136390686},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5979962944984436},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5834054946899414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5338403582572937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5044761896133423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48817116022109985},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.4672280251979828},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.460345059633255},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45740818977355957},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.42891842126846313},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4205617308616638},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3769993782043457},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36632847785949707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3417798578739166},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.17633694410324097},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/19m1236886","is_oa":true,"landing_page_url":"https://doi.org/10.1137/19m1236886","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/19M1236886","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1137/19m1236886","is_oa":true,"landing_page_url":"https://doi.org/10.1137/19m1236886","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/19M1236886","source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970812740.pdf","grobid_xml":"https://content.openalex.org/works/W2970812740.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1600402929","https://openalex.org/W1686810756","https://openalex.org/W1760551737","https://openalex.org/W2029213856","https://openalex.org/W2076434944","https://openalex.org/W2082233060","https://openalex.org/W2118550318","https://openalex.org/W2138621090","https://openalex.org/W2148603752","https://openalex.org/W2154579312","https://openalex.org/W2157364932","https://openalex.org/W2194775991","https://openalex.org/W2335728318","https://openalex.org/W2407712691","https://openalex.org/W2520774990","https://openalex.org/W2682189153","https://openalex.org/W2963291430","https://openalex.org/W2963446712","https://openalex.org/W2964330148","https://openalex.org/W3099206234","https://openalex.org/W3118608800","https://openalex.org/W3137695714","https://openalex.org/W4236965008","https://openalex.org/W4285719527","https://openalex.org/W4300101671"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W3095152779","https://openalex.org/W3119773509","https://openalex.org/W3128220219","https://openalex.org/W3006353185","https://openalex.org/W4300326282","https://openalex.org/W2742395793","https://openalex.org/W2810018382"],"abstract_inverted_index":{"Deep":[0],"neural":[1,65],"networks":[2],"(DNNs)":[3],"typically":[4],"have":[5],"enough":[6],"capacity":[7,164],"to":[8,146],"fit":[9],"random":[10,148,151],"data":[11,149],"by":[12,160],"brute":[13],"force":[14],"even":[15],"when":[16,127,133],"conventional":[17,125,142],"data-dependent":[18,60],"regularizations":[19],"focusing":[20],"on":[21,73,81,129],"the":[22,25,33,38,41,45,63,70,91,100,134,162,166],"geometry":[23,43,71],"of":[24,76,98,107,165],"features":[26,77,111],"are":[27,137],"imposed.":[28],"We":[29,93],"find":[30],"out":[31],"that":[32,120,154],"reason":[34],"for":[35,59],"this":[36],"is":[37,78,105],"inconsistency":[39],"between":[40],"enforced":[42,72],"and":[44],"standard":[46],"softmax":[47],"cross":[48],"entropy":[49],"loss.":[50],"To":[51],"resolve":[52],"this,":[53],"we":[54],"propose":[55],"a":[56,82,86,95],"new":[57],"framework":[58],"DNN":[61],"regularization,":[62],"Geometrically-Regularized-Self-Validating":[64],"Networks":[66],"(GRSVNet).":[67],"During":[68],"training,":[69],"one":[74],"batch":[75,84],"simultaneously":[79],"validated":[80],"separate":[83],"using":[85],"validation":[87],"loss":[88],"consistent":[89],"with":[90,124],"geometry.":[92],"study":[94],"particular":[96],"case":[97],"GRSVNet,":[99],"Orthogonal-Low-rank":[101],"Embedding":[102],"(OLE)-GRSVNet,":[103],"which":[104],"capable":[106],"producing":[108],"highly":[109],"discriminative":[110],"residing":[112],"in":[113],"orthogonal":[114],"low-rank":[115],"subspaces.":[116],"Numerical":[117],"experiments":[118],"show":[119],"OLE-GRSVNet":[121,144],"outperforms":[122],"DNNs":[123],"regularization":[126],"trained":[128],"real":[130],"data,":[131],"especially":[132],"training":[135],"samples":[136],"scarce.":[138],"More":[139],"importantly,":[140],"unlike":[141],"DNNs,":[143],"refuses":[145],"memorize":[147],"or":[150],"labels,":[152],"suggesting":[153],"it":[155],"only":[156],"learns":[157],"intrinsic":[158],"patterns":[159],"reducing":[161],"memorizing":[163],"baseline":[167],"DNN.":[168]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}