{"id":"https://openalex.org/W7163124234","doi":"https://doi.org/10.48550/arxiv.2606.00289","title":"Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms","display_name":"Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163124234","doi":"https://doi.org/10.48550/arxiv.2606.00289"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00289","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":null,"license_id":null,"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.2606.00289","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137690265","display_name":"Nathan White","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"White, Nathan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137623627","display_name":"Krish Singal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singal, Krish","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.35929998755455017,"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":0.35929998755455017,"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":0.2029999941587448,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.0738999992609024,"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/quantization","display_name":"Quantization (signal processing)","score":0.7612000107765198},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5766000151634216},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40849998593330383},{"id":"https://openalex.org/keywords/inner-product-space","display_name":"Inner product space","score":0.36730000376701355},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.3564000129699707},{"id":"https://openalex.org/keywords/learning-vector-quantization","display_name":"Learning vector quantization","score":0.325300008058548}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7612000107765198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.651199996471405},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5766000151634216},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5178999900817871},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C91855343","wikidata":"https://www.wikidata.org/wiki/Q214159","display_name":"Inner product space","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3328000009059906},{"id":"https://openalex.org/C40567965","wikidata":"https://www.wikidata.org/wiki/Q1820283","display_name":"Learning vector quantization","level":3,"score":0.325300008058548},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30820000171661377},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26249998807907104},{"id":"https://openalex.org/C93372532","wikidata":"https://www.wikidata.org/wiki/Q6552455","display_name":"Linde\u2013Buzo\u2013Gray algorithm","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00289","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.00289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00289","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Quantization":[0,103],"is":[1],"a":[2,16,93,127],"fundamental":[3],"tool":[4],"used":[5],"to":[6,54,135],"compress":[7],"datasets,":[8],"neural":[9],"network":[10],"weights,":[11],"and":[12,70,73,84,110,154,165],"memory":[13],"usage":[14],"in":[15,52,167],"range":[17],"of":[18,24,37,89,100,129],"computational":[19],"tasks.":[20],"Many":[21],"downstream":[22],"applications":[23],"vector":[25],"quantization":[26,41,75,161],"perform":[27,124],"inner":[28,38,46,80],"products":[29,47,81],"with":[30,48,82,96],"arbitrary":[31],"inputs.":[32,86],"This":[33],"motivates":[34],"the":[35,57,97],"study":[36],"product":[39],"aware":[40],"schemes":[42],"that":[43,66,77,123],"approximately":[44,78],"preserve":[45,79],"unseen":[49],"vectors":[50],"--":[51],"contrast":[53],"simply":[55],"minimizing":[56],"mean-squared":[58],"error.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"formulate":[64],"objectives":[65,91],"capture":[67],"natural":[68],"desiderata":[69],"develop":[71,106],"adaptive":[72,160],"unbiased":[74],"methods":[76,148],"worst-case":[83],"average-case":[85],"An":[87],"analysis":[88],"these":[90],"shows":[92],"tight":[94],"connection":[95],"well-studied":[98],"notion":[99],"Adaptive":[101],"Stochastic":[102],"(ASQ).":[104],"We":[105],"provably":[107],"fast":[108],"exact":[109],"approximate":[111],"algorithms":[112,122,137],"for":[113,138],"our":[114],"objectives.":[115],"Our":[116],"theoretical":[117,153],"results":[118,156],"inspire":[119],"efficient":[120,164],"practical":[121,136,168],"well":[125],"across":[126],"variety":[128],"workload":[130],"distributions.":[131],"They":[132],"also":[133],"lead":[134],"standard":[139],"ASQ":[140],"which":[141],"are":[142],"2-10$\\times$":[143],"faster":[144],"than":[145],"prior":[146],"state-of-the-art":[147],"while":[149],"maintaining":[150],"quality.":[151],"These":[152],"empirical":[155],"contribute":[157],"towards":[158],"making":[159],"techniques":[162],"more":[163],"tractable":[166],"settings.":[169]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}