{"id":"https://openalex.org/W4416251821","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229409","title":"Reshaping Cross-Entropy Non-Convex Properties through Normalized Risk-Averse Loss","display_name":"Reshaping Cross-Entropy Non-Convex Properties through Normalized Risk-Averse Loss","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251821","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229409"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5028709578","display_name":"Weihao Xia","orcid":"https://orcid.org/0000-0003-0087-3525"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weihao Xia","raw_affiliation_strings":["Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011057071","display_name":"Huachuan Wang","orcid":"https://orcid.org/0000-0001-5307-3690"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huachuan Wang","raw_affiliation_strings":["Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101724686","display_name":"Yuhang Sun","orcid":"https://orcid.org/0009-0001-8394-7843"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Sun","raw_affiliation_strings":["Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024792291","display_name":"Enshuo Yan","orcid":"https://orcid.org/0009-0006-5843-4890"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enshuo Yan","raw_affiliation_strings":["Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,College of Intelligent Systems Science and Engineering,Harbin,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104056506","display_name":"James Lo","orcid":null},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Lo","raw_affiliation_strings":["University of Maryland Baltimore County,Department of Mathematics and Statistics,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland Baltimore County,Department of Mathematics and Statistics,Baltimore,USA","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028709578"],"corresponding_institution_ids":["https://openalex.org/I151727225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19493577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.8503999710083008,"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":0.8503999710083008,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0478999987244606,"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":0.01860000006854534,"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/robustness","display_name":"Robustness (evolution)","score":0.7208999991416931},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6636999845504761},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6013000011444092},{"id":"https://openalex.org/keywords/convexity","display_name":"Convexity","score":0.5706999897956848},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5002999901771545},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.49059998989105225},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.43299999833106995}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7208999991416931},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6636999845504761},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6013000011444092},{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5170999765396118},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5002999901771545},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.487199991941452},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3865000009536743},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3084000051021576},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.25270000100135803},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W2136619318","https://openalex.org/W2194775991","https://openalex.org/W2261232712","https://openalex.org/W3011132328","https://openalex.org/W3135149588","https://openalex.org/W3136021864","https://openalex.org/W3140913729","https://openalex.org/W3190730109","https://openalex.org/W3194383713","https://openalex.org/W3198924441","https://openalex.org/W4225466681"],"related_works":[],"abstract_inverted_index":{"Non-convex":[0],"optimization":[1,79,103],"poses":[2],"significant":[3],"challenges":[4],"in":[5],"training":[6],"deep":[7],"neural":[8,116],"networks,":[9],"often":[10],"leading":[11,138],"to":[12,17,37,66,139],"suboptimal":[13,59],"solutions":[14],"by":[15,48],"converging":[16],"local":[18],"rather":[19],"than":[20,105],"global":[21,84],"minima.":[22],"To":[23],"address":[24],"this,":[25],"we":[26],"propose":[27],"the":[28,45,55,64,70,125],"Normalized":[29],"Risk-Averse":[30],"Cross-Entropy":[31,46,127],"(NRACE)":[32],"loss":[33,47,107,128],"function,":[34],"specifically":[35],"designed":[36],"improve":[38],"generalization":[39,133],"and":[40,115,135],"convergence":[41],"behavior.":[42],"NRACE":[43,131],"extends":[44],"introducing":[49],"a":[50],"normalized":[51],"risk-averse":[52],"term,":[53],"enhancing":[54],"model\u2019s":[56],"robustness":[57],"against":[58],"solutions.":[60,141],"This":[61],"term":[62],"encourages":[63],"model":[65],"prioritize":[67],"regions":[68],"of":[69,83],"parameter":[71],"space":[72],"associated":[73],"with":[74,96,124],"lower":[75],"risk,":[76],"thereby":[77],"guiding":[78],"toward":[80],"improved":[81],"approximations":[82],"optima.":[85],"Our":[86],"theoretical":[87],"analysis":[88,123],"demonstrates":[89,129],"that":[90,130],"NRACE\u2019s":[91,120],"convexity":[92],"region":[93],"expands":[94],"monotonically":[95],"its":[97],"risk":[98],"sensitivity":[99],"index,":[100],"providing":[101],"stronger":[102],"guarantees":[104],"traditional":[106,126],"functions.":[108],"Empirical":[109],"experiments":[110],"across":[111],"various":[112],"benchmark":[113],"datasets":[114],"network":[117],"architectures":[118],"validate":[119],"effectiveness.":[121],"Comparative":[122],"improves":[132],"performance":[134],"accelerates":[136],"convergence,":[137],"higher-quality":[140]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}