{"id":"https://openalex.org/W4407263652","doi":"https://doi.org/10.1007/s10994-024-06661-5","title":"Per-example gradient regularization improves learning signals from noisy data","display_name":"Per-example gradient regularization improves learning signals from noisy data","publication_year":2025,"publication_date":"2025-02-07","ids":{"openalex":"https://openalex.org/W4407263652","doi":"https://doi.org/10.1007/s10994-024-06661-5"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-024-06661-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06661-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06661-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06661-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051055590","display_name":"Xuran Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xuran Meng","raw_affiliation_strings":["Department of Biostatistics, Umich, Ann Arbor, 48109, United States"],"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Umich, Ann Arbor, 48109, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015347934","display_name":"Yuan Cao","orcid":"https://orcid.org/0000-0001-6631-4908"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuan Cao","raw_affiliation_strings":["Department of Statistics and Actuarial Science, HKU, Hong Kong, 999077, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and Actuarial Science, HKU, Hong Kong, 999077, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085848346","display_name":"Difan Zou","orcid":"https://orcid.org/0000-0002-6544-2593"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Difan Zou","raw_affiliation_strings":["Department of Computer Science and Institute of Data Science, HKU, Hong Kong, 999077, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Institute of Data Science, HKU, Hong Kong, 999077, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051055590"],"corresponding_institution_ids":[],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":4.3275,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92169956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"114","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9972000122070312,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6746749877929688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.55305415391922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5017728805541992},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4275251030921936},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4086039662361145},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36320188641548157}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6746749877929688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.55305415391922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5017728805541992},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4275251030921936},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4086039662361145},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36320188641548157}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10994-024-06661-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06661-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06661-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:hub.hku.hk:10722/358381","is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/358381","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s10994-024-06661-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06661-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06661-5.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4407263652.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2523060838","https://openalex.org/W2895616758","https://openalex.org/W2912811302","https://openalex.org/W2940107683","https://openalex.org/W2990138404","https://openalex.org/W2992043355","https://openalex.org/W3018252856","https://openalex.org/W3020361330","https://openalex.org/W3035233211","https://openalex.org/W3091401866","https://openalex.org/W3113303810","https://openalex.org/W3120901154","https://openalex.org/W3138832176","https://openalex.org/W3157730063","https://openalex.org/W3172995164","https://openalex.org/W3193779740","https://openalex.org/W3204187020","https://openalex.org/W4221142204","https://openalex.org/W4221158304","https://openalex.org/W4226320345","https://openalex.org/W4298040530","https://openalex.org/W4308830743","https://openalex.org/W4320233696","https://openalex.org/W4323651343","https://openalex.org/W6783271219","https://openalex.org/W6809695159","https://openalex.org/W6842354201"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Gradient":[0],"regularization,":[1],"as":[2],"described":[3],"in":[4,70,158],"Barrett":[5],"and":[6,61,75,98,162],"Dherin":[7],"(in:":[8],"International":[9],"conference":[10],"on":[11],"learning":[12,41,160],"representations,":[13],"2021),":[14],"is":[15],"a":[16,63,83],"highly":[17],"effective":[18,169],"technique":[19,33],"for":[20,166],"promoting":[21],"flat":[22],"minima":[23],"during":[24],"gradient":[25,58,113],"descent.":[26],"Empirical":[27],"evidence":[28],"suggests":[29],"that":[30,66,100,131],"this":[31,52],"regularization":[32,59],"can":[34,102],"significantly":[35],"enhance":[36],"the":[37,56,118,121,134,142,147,153],"robustness":[38,76],"of":[39,136,144,155],"deep":[40,159],"models":[42],"against":[43,77],"noisy":[44],"perturbations,":[45],"while":[46,106],"also":[47],"reducing":[48],"test":[49,73],"error.":[50],"In":[51,110],"paper,":[53],"we":[54,81],"explore":[55],"per-example":[57],"(PEGR)":[60],"present":[62],"theoretical":[64],"analysis":[65,129],"demonstrates":[67],"its":[68],"effectiveness":[69],"improving":[71],"both":[72],"error":[74],"noise":[78,108],"perturbations.":[79],"Specifically,":[80],"adopt":[82],"signal-noise":[84],"data":[85],"model":[86],"from":[87,120,146],"Cao":[88],"et":[89],"al.":[90],"(Adv":[91],"Neural":[92],"Inf":[93],"Process":[94],"Syst":[95],"35:25237\u201325250,":[96],"2022)":[97],"show":[99],"PEGR":[101,132],"learn":[103],"signals":[104],"effectively":[105,140],"suppressing":[107,141],"memorization.":[109],"contrast,":[111],"standard":[112],"descent":[114],"struggles":[115],"to":[116,124],"distinguish":[117],"signal":[119],"noise,":[122],"leading":[123],"suboptimal":[125],"generalization":[126],"performance.":[127],"Our":[128],"reveals":[130],"penalizes":[133],"variance":[135,156],"pattern":[137],"learning,":[138],"thus":[139],"memorization":[143],"noises":[145],"training":[148,161,170],"data.":[149],"These":[150],"findings":[151],"underscore":[152],"importance":[154],"control":[157],"offer":[163],"useful":[164],"insights":[165],"developing":[167],"more":[168],"approaches.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}