{"id":"https://openalex.org/W4405468238","doi":"https://doi.org/10.1109/iccv51701.2025.02101","title":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization","display_name":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405468238","doi":"https://doi.org/10.1109/iccv51701.2025.02101"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.10663","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036610839","display_name":"Jingyang Li","orcid":"https://orcid.org/0000-0002-1857-3814"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingyang Li","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104183700","display_name":"Kuangyu Ding","orcid":"https://orcid.org/0000-0002-5131-2106"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kuangyu Ding","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064083862","display_name":"Kim-Chuan Toh","orcid":"https://orcid.org/0000-0001-7204-8933"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kim-Chuan Toh","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103055255","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0001-9496-8810"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22633","last_page":"22643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11321","display_name":"Error Correcting Code Techniques","score":0.8450999855995178,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11321","display_name":"Error Correcting Code Techniques","score":0.8450999855995178,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/bit","display_name":"Bit (key)","score":0.6899875402450562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5263993740081787},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4420890808105469},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3495748043060303},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29218313097953796},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08921489119529724}],"concepts":[{"id":"https://openalex.org/C117011727","wikidata":"https://www.wikidata.org/wiki/Q1278488","display_name":"Bit (key)","level":2,"score":0.6899875402450562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5263993740081787},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4420890808105469},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3495748043060303},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29218313097953796},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08921489119529724}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.02101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.10663","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10663","pdf_url":"https://arxiv.org/pdf/2412.10663","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-11461","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/10459","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://iccv.thecvf.com/Conferences/2025/AcceptedPapers","raw_type":"Conference Proceeding Article"},{"id":"doi:10.48550/arxiv.2412.10663","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.10663","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.10663","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10663","pdf_url":"https://arxiv.org/pdf/2412.10663","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8435979052","display_name":null,"funder_award_id":"T2EP20224-0048","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405468238.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4327546585","https://openalex.org/W2411923897","https://openalex.org/W4394546135","https://openalex.org/W4285347720","https://openalex.org/W4200259850","https://openalex.org/W2333831899","https://openalex.org/W2484894494"],"abstract_inverted_index":{"Preconditioned":[0],"stochastic":[1,161],"optimization":[2,162],"algorithms,":[3],"exemplified":[4],"by":[5,10,59,68],"Shampoo,":[6],"outperform":[7],"first-order":[8],"optimizers":[9],"offering":[11],"theoretical":[12],"convergence":[13,151],"benefits":[14],"and":[15,111,117,140,159],"practical":[16],"gains":[17],"in":[18,103,114,143],"large-scale":[19,144],"neural":[20],"network":[21],"training.":[22],"However,":[23],"they":[24],"incur":[25],"substantial":[26],"memory":[27,66,138],"overhead":[28],"due":[29],"to":[30,79,93],"the":[31,62,88,104,115,122],"storage":[32],"demands":[33],"of":[34,61,96,121],"non-diagonal":[35],"preconditioning":[36],"matrices.":[37],"To":[38,83],"address":[39],"this,":[40],"we":[41,54,99,128,148],"introduce":[42,49],"4-bit":[43],"quantization":[44,60,90,105,133],"for":[45,153],"Shampoo's":[46],"preconditioners.":[47,97],"We":[48],"two":[50],"key":[51],"methods:":[52],"First,":[53],"apply":[55],"Cholesky":[56,63,94,109,132],"decomposition":[57],"followed":[58],"factors,":[64],"reducing":[65],"usage":[67],"leveraging":[69],"their":[70],"lower":[71,116],"triangular":[72,119],"structure":[73],"while":[74],"better":[75],"preserving":[76],"spectral":[77],"properties":[78],"minimize":[80],"information":[81],"loss.":[82],"our":[84],"knowledge,":[85],"this":[86],"is":[87],"first":[89],"approach":[91],"applied":[92],"factors":[95],"Second,":[98],"incorporate":[100],"error":[101,112,135],"feedback":[102,136],"process,":[106],"efficiently":[107],"storing":[108],"factor":[110],"state":[113],"upper":[118],"parts":[120],"same":[123],"matrix.":[124],"Through":[125],"extensive":[126],"experiments,":[127],"demonstrate":[129],"that":[130],"combining":[131],"with":[134],"enhances":[137],"efficiency":[139],"algorithm":[141],"performance":[142],"deep-learning":[145],"tasks.":[146],"Theoretically,":[147],"also":[149],"provide":[150],"proofs":[152],"quantized":[154],"Shampoo":[155],"under":[156],"both":[157],"smooth":[158],"non-smooth":[160],"settings.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}