{"id":"https://openalex.org/W4406461985","doi":"https://doi.org/10.1109/bigdata62323.2024.10825352","title":"NysAct: A Scalable Preconditioned Gradient Descent using Nystr\u00f6m Approximation","display_name":"NysAct: A Scalable Preconditioned Gradient Descent using Nystr\u00f6m Approximation","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406461985","doi":"https://doi.org/10.1109/bigdata62323.2024.10825352"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.08360","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036210359","display_name":"Hyunseok Seung","orcid":"https://orcid.org/0000-0002-5921-915X"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hyunseok Seung","raw_affiliation_strings":["University of Georgia,Department of Statistics,Athens,USA"],"affiliations":[{"raw_affiliation_string":"University of Georgia,Department of Statistics,Athens,USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100415736","display_name":"Jaewoo Lee","orcid":"https://orcid.org/0000-0002-7418-651X"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaewoo Lee","raw_affiliation_strings":["University of Georgia,School of Computing,Athens,USA"],"affiliations":[{"raw_affiliation_string":"University of Georgia,School of Computing,Athens,USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048508533","display_name":"Hyunsuk Ko","orcid":"https://orcid.org/0000-0002-7015-8351"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunsuk Ko","raw_affiliation_strings":["Hanyang University,School of Electrical Engineering,Ansan,South Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,School of Electrical Engineering,Ansan,South Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036210359"],"corresponding_institution_ids":["https://openalex.org/I165733156"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23761043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1442","last_page":"1449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9980999827384949,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.996399998664856,"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/scalability","display_name":"Scalability","score":0.5391519069671631},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.510665237903595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5083798766136169},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.4405781030654907},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.39113473892211914},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37870678305625916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3354375958442688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23177585005760193},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.06598448753356934}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5391519069671631},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.510665237903595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5083798766136169},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4405781030654907},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.39113473892211914},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37870678305625916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3354375958442688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23177585005760193},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.06598448753356934},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.08360","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08360","pdf_url":"https://arxiv.org/pdf/2506.08360","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.08360","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08360","pdf_url":"https://arxiv.org/pdf/2506.08360","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W1994616650","https://openalex.org/W2005136695","https://openalex.org/W2038210983","https://openalex.org/W2056641273","https://openalex.org/W2078409719","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2950082039","https://openalex.org/W2963446712","https://openalex.org/W3031420959","https://openalex.org/W3035182906","https://openalex.org/W3118608800","https://openalex.org/W3179101329","https://openalex.org/W3186067722","https://openalex.org/W3204947518","https://openalex.org/W4283802681","https://openalex.org/W4293363567","https://openalex.org/W4405008685","https://openalex.org/W6676930901","https://openalex.org/W6683107984","https://openalex.org/W6726497184","https://openalex.org/W6740285172","https://openalex.org/W6748982233","https://openalex.org/W6757817989","https://openalex.org/W6762990414","https://openalex.org/W6779861650","https://openalex.org/W6787972765","https://openalex.org/W6788135285","https://openalex.org/W6798025856","https://openalex.org/W6803653593","https://openalex.org/W6810634299","https://openalex.org/W6852587669","https://openalex.org/W7000331227"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3008318776","https://openalex.org/W1977633006","https://openalex.org/W1971945429","https://openalex.org/W2041416246"],"abstract_inverted_index":{"Adaptive":[0],"gradient":[1,41],"methods":[2,19,103],"are":[3],"computationally":[4],"efficient":[5],"and":[6,22,29,51,77,101],"converge":[7],"quickly,":[8],"but":[9,24,104],"they":[10],"often":[11],"suffer":[12],"from":[13],"poor":[14],"generalization.":[15],"In":[16,32],"contrast,":[17],"second-order":[18,52,102,113],"enhance":[20],"convergence":[21],"generalization":[23],"typically":[25],"incur":[26],"high":[27],"computational":[28,109],"memory":[30,78],"costs.":[31],"this":[33],"work,":[34],"we":[35],"introduce":[36],"NYSACT,":[37],"a":[38,46,71],"scalable":[39],"first-order":[40,50,100],"preconditioning":[42,72],"method":[43,60],"that":[44,89],"strikes":[45],"balance":[47],"between":[48],"state-of-the-art":[49],"optimization":[53],"methods.":[54,114],"NYSACT":[55,90],"leverages":[56],"an":[57],"eigenvalue-shifted":[58],"Nystr\u00f6m":[59],"to":[61,98],"approximate":[62],"the":[63],"activation":[64],"covariance":[65],"matrix,":[66,73],"which":[67],"is":[68],"used":[69],"as":[70],"significantly":[74],"reducing":[75],"time":[76],"complexities":[79],"with":[80],"minimal":[81],"impact":[82],"on":[83],"test":[84,95],"accuracy.":[85],"Our":[86],"experiments":[87],"show":[88],"not":[91],"only":[92],"achieves":[93],"improved":[94],"accuracy":[96],"compared":[97],"both":[99],"also":[105],"demands":[106],"considerably":[107],"less":[108],"resources":[110],"than":[111],"existing":[112]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}