{"id":"https://openalex.org/W4402351277","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650665","title":"SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrix","display_name":"SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrix","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351277","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650665"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5044190873","display_name":"Mrinmay Sen","orcid":"https://orcid.org/0000-0002-8810-0502"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mrinmay Sen","raw_affiliation_strings":["Swinburne University of Technology,Dept. of Computing Technologies,Hawthorn,Victoria,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology,Dept. of Computing Technologies,Hawthorn,Victoria,Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006614329","display_name":"A. K. Qin","orcid":"https://orcid.org/0000-0001-6631-1651"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"A. K. Qin","raw_affiliation_strings":["Swinburne University of Technology,Dept. of Computing Technologies,Hawthorn,Victoria,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swinburne University of Technology,Dept. of Computing Technologies,Hawthorn,Victoria,Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113413906","display_name":"C. Gayathri","orcid":null},"institutions":[{"id":"https://openalex.org/I1336379959","display_name":"Mahindra Group (India)","ror":"https://ror.org/05mxsz225","country_code":"IN","type":"company","lineage":["https://openalex.org/I1336379959"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gayathri C","raw_affiliation_strings":["Mahindra University,Dept. of Computer Science and Engineering,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mahindra University,Dept. of Computer Science and Engineering,Hyderabad,India","institution_ids":["https://openalex.org/I1336379959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101313929","display_name":"Raghu Kishore N","orcid":null},"institutions":[{"id":"https://openalex.org/I1336379959","display_name":"Mahindra Group (India)","ror":"https://ror.org/05mxsz225","country_code":"IN","type":"company","lineage":["https://openalex.org/I1336379959"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raghu Kishore N","raw_affiliation_strings":["Mahindra University,Dept. of Computer Science and Engineering,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mahindra University,Dept. of Computer Science and Engineering,Hyderabad,India","institution_ids":["https://openalex.org/I1336379959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044216245","display_name":"Yen\u2010Wei Chen","orcid":"https://orcid.org/0000-0002-5952-0188"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yen-Wei Chen","raw_affiliation_strings":["Ritsumeikan University,Dept. of Information Science and Engineering,Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Dept. of Information Science and Engineering,Kyoto,Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030765476","display_name":"Balasubramanian Raman","orcid":"https://orcid.org/0000-0001-6277-6267"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Balasubramanian Raman","raw_affiliation_strings":["Indian Institute of Technology Roorkee,Dept. of Computer Science and Engineering,Roorkee,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee,Dept. of Computer Science and Engineering,Roorkee,India","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9991999864578247,"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/T10320","display_name":"Neural Networks and Applications","score":0.9991999864578247,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9991000294685364,"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/T10057","display_name":"Face and Expression Recognition","score":0.998199999332428,"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/fisher-information","display_name":"Fisher information","score":0.7125407457351685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5656077861785889},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4548337161540985},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4457653760910034},{"id":"https://openalex.org/keywords/matrix-algebra","display_name":"Matrix algebra","score":0.4243772625923157},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3491607904434204},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3388928771018982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32650142908096313},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15268674492835999},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08309221267700195}],"concepts":[{"id":"https://openalex.org/C29406490","wikidata":"https://www.wikidata.org/wiki/Q1420659","display_name":"Fisher information","level":2,"score":0.7125407457351685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5656077861785889},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4548337161540985},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4457653760910034},{"id":"https://openalex.org/C2988995629","wikidata":"https://www.wikidata.org/wiki/Q2915729","display_name":"Matrix algebra","level":3,"score":0.4243772625923157},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3491607904434204},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3388928771018982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32650142908096313},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15268674492835999},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08309221267700195},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1416942850","https://openalex.org/W1522301498","https://openalex.org/W1970789124","https://openalex.org/W1984447710","https://openalex.org/W1984845482","https://openalex.org/W2051434435","https://openalex.org/W2066671570","https://openalex.org/W2078394884","https://openalex.org/W2107438106","https://openalex.org/W2146502635","https://openalex.org/W2150871663","https://openalex.org/W2606981059","https://openalex.org/W2772124661","https://openalex.org/W2963433607","https://openalex.org/W2963941964","https://openalex.org/W2964155733","https://openalex.org/W2982486887","https://openalex.org/W3031420959","https://openalex.org/W3086499488","https://openalex.org/W4286795653","https://openalex.org/W4299356270","https://openalex.org/W6629379589","https://openalex.org/W6631190155","https://openalex.org/W6640590530","https://openalex.org/W6676105031","https://openalex.org/W6681435938","https://openalex.org/W6683107984","https://openalex.org/W6721263324","https://openalex.org/W6741489008","https://openalex.org/W6773732629","https://openalex.org/W6840619102"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W3012088032","https://openalex.org/W2238904537","https://openalex.org/W2073681303","https://openalex.org/W2776312158","https://openalex.org/W1965458961","https://openalex.org/W4294328901","https://openalex.org/W2042150869","https://openalex.org/W3185610468","https://openalex.org/W2952582351"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,47],"new":[4],"stochastic":[5,36,134],"optimization":[6,37,167],"method":[7],"based":[8],"on":[9,143],"the":[10,22,26,54,60,69,75,85,91,95,99,113,122,127,156,172,177],"regularized":[11,70,114],"Fisher":[12],"information":[13],"matrix":[14,28,81,118],"(FIM),":[15],"named":[16],"SOFIM,":[17],"which":[18],"can":[19,43],"efficiently":[20],"utilize":[21],"FIM":[23,62,71,115],"to":[24,97,107,121],"approximate":[25],"Hessian":[27],"for":[29,175],"finding":[30,74],"Newton\u2019s":[31],"gradient":[32,51,76,96,135],"update":[33,77],"in":[34,169],"large-scale":[35],"of":[38,49,56,68,94,101,112,171,180],"machine":[39],"learning":[40,146],"models.":[41],"It":[42],"be":[44],"viewed":[45],"as":[46,133,185,187],"variant":[48],"natural":[50],"descent,":[52],"where":[53],"challenge":[55],"storing":[57],"and":[58,72,116,130,163,182],"calculating":[59],"full":[61],"is":[63],"addressed":[64],"through":[65],"making":[66],"use":[67],"directly":[73],"direction":[78],"via":[79],"Sherman-Morrison":[80,117],"inversion.":[82],"Additionally,":[83],"like":[84],"popular":[86],"Adam":[87],"method,":[88],"SOFIM":[89,158],"uses":[90],"first":[92],"moment":[93],"address":[98],"issue":[100],"non-stationary":[102],"objectives":[103,179],"across":[104],"mini-batches":[105],"due":[106],"heterogeneous":[108],"data.":[109],"The":[110,140],"utilization":[111],"inversion":[119],"leads":[120],"improved":[123],"convergence":[124,173],"rate":[125],"with":[126,138,161],"same":[128],"space":[129],"time":[131],"complexities":[132],"descent":[136],"(SGD)":[137],"momentum.":[139],"extensive":[141],"experiments":[142],"training":[144,181],"deep":[145],"models":[147],"using":[148],"several":[149,164],"benchmark":[150],"image":[151],"classification":[152],"datasets":[153],"demonstrate":[154],"that":[155],"proposed":[157],"outperforms":[159],"SGD":[160],"momentum":[162],"state-of-the-art":[165],"Newton":[166],"methods":[168],"term":[170],"speed":[174],"achieving":[176],"pre-specified":[178],"test":[183,188],"losses":[184],"well":[186],"accuracy.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}