{"id":"https://openalex.org/W7152684082","doi":"https://doi.org/10.48550/arxiv.2604.06689","title":"Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classification","display_name":"Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classification","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7152684082","doi":"https://doi.org/10.48550/arxiv.2604.06689"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.06689","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06689","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.06689","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124113406","display_name":"Qipeng Zhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhan, Qipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124135130","display_name":"Zhuoping Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zhuoping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133288589","display_name":"Li Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.1477999985218048,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.1477999985218048,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.1339000016450882,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11420000344514847,"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/overfitting","display_name":"Overfitting","score":0.8230999708175659},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7386999726295471},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6983000040054321},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49729999899864197},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.45179998874664307},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4422000050544739},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4059000015258789}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8230999708175659},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7386999726295471},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6983000040054321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6534000039100647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5634999871253967},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46650001406669617},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4050999879837036},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37279999256134033},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3142000138759613},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.06689","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06689","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.06689","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06689","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7737855315208435,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-entropy":[0],"(CE)":[1],"is":[2,14,40,147,158],"the":[3,25,36,49,88,103,108,119,123,126,136,162],"default":[4],"training":[5,37,127],"loss":[6],"for":[7,73],"supervised":[8],"classification,":[9],"but":[10],"its":[11,155],"sample":[12],"efficiency":[13],"limited":[15],"when":[16],"labels":[17],"are":[18],"scarce.":[19],"Existing":[20],"remedies":[21],"primarily":[22],"act":[23],"on":[24,48,122,168],"data":[26],"side,":[27],"via":[28],"augmentation,":[29],"synthesis,":[30],"or":[31,90],"transfer":[32],"from":[33,98],"pretrained":[34],"models;":[35],"objective":[38],"itself":[39],"rarely":[41],"revisited.":[42],"We":[43,134],"revisit":[44],"it":[45],"here.":[46],"Drawing":[47],"classical":[50],"observation":[51],"that":[52,75,145],"generative":[53,78],"classifiers":[54],"reach":[55],"their":[56],"asymptotic":[57],"error":[58],"with":[59],"fewer":[60],"samples":[61],"than":[62],"discriminative":[63,84],"ones,":[64],"we":[65],"propose":[66],"Generative":[67],"Cross-Entropy":[68],"(GenCE),":[69],"a":[70,77,82,92,99,132,151],"drop-in":[71],"replacement":[72],"CE":[74,181],"introduces":[76],"learning":[79],"principle":[80],"into":[81],"standard":[83],"network":[85],"without":[86],"altering":[87],"architecture":[89],"fitting":[91],"separate":[93],"density":[94],"model.":[95],"GenCE":[96,146,179],"follows":[97],"Bayesian":[100],"rewrite":[101],"of":[102],"class-conditional":[104],"likelihood":[105],"and,":[106],"in":[107,172],"mini-batch":[109],"approximation,":[110],"reduces":[111],"to":[112,139],"normalizing":[113],"each":[114],"sample's":[115],"softmax":[116],"score":[117],"against":[118],"model's":[120],"predictions":[121],"batch,":[124],"coupling":[125],"signal":[128],"across":[129],"examples":[130],"sharing":[131],"class.":[133],"extend":[135],"proper-scoring-rule":[137],"framework":[138],"such":[140],"non-local":[141],"losses":[142],"and":[143,171,176,182,192],"prove":[144],"strictly":[148],"proper":[149],"under":[150],"mild":[152],"completeness":[153],"condition:":[154],"population":[156],"risk":[157],"uniquely":[159],"minimized":[160],"at":[161],"true":[163],"posterior.":[164],"Across":[165],"three":[166],"datasets,":[167],"two":[169],"architectures":[170],"both":[173],"balanced":[174],"small-data":[175],"class-imbalanced":[177],"regimes,":[178],"outperforms":[180],"other":[183],"widely":[184],"used":[185],"losses,":[186],"while":[187],"also":[188],"producing":[189],"better-calibrated":[190],"probabilities":[191],"stronger":[193],"out-of-distribution":[194],"detection.":[195]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-10T00:00:00"}