{"id":"https://openalex.org/W3162998282","doi":"https://doi.org/10.32473/flairs.v34i1.128568","title":"Learning from low precision samples","display_name":"Learning from low precision samples","publication_year":2021,"publication_date":"2021-04-18","ids":{"openalex":"https://openalex.org/W3162998282","doi":"https://doi.org/10.32473/flairs.v34i1.128568","mag":"3162998282"},"language":"en","primary_location":{"id":"doi:10.32473/flairs.v34i1.128568","is_oa":true,"landing_page_url":"https://doi.org/10.32473/flairs.v34i1.128568","pdf_url":"https://journals.flvc.org/FLAIRS/article/download/128568/130023","source":{"id":"https://openalex.org/S4210205383","display_name":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","issn_l":"2334-0754","issn":["2334-0754","2334-0762"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310320363","host_organization_name":"George A. Smathers Libraries","host_organization_lineage":["https://openalex.org/P4310320363"],"host_organization_lineage_names":["George A. Smathers Libraries"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International FLAIRS Conference Proceedings","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://journals.flvc.org/FLAIRS/article/download/128568/130023","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043536690","display_name":"Ji In Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131443","display_name":"Center for Health and Gender Equity","ror":"https://ror.org/02wf58e57","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210131443"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ji In Choi","raw_affiliation_strings":["Columbia University, Equal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, Equal","institution_ids":["https://openalex.org/I4210131443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061896802","display_name":"Madeleine Georges","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131443","display_name":"Center for Health and Gender Equity","ror":"https://ror.org/02wf58e57","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210131443"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madeleine Georges","raw_affiliation_strings":["Columbia University, Equal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, Equal","institution_ids":["https://openalex.org/I4210131443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113803464","display_name":"Jung Ah Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131443","display_name":"Center for Health and Gender Equity","ror":"https://ror.org/02wf58e57","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210131443"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jung Ah Shin","raw_affiliation_strings":["Columbia University, Equal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, Equal","institution_ids":["https://openalex.org/I4210131443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052355036","display_name":"Olivia Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131443","display_name":"Center for Health and Gender Equity","ror":"https://ror.org/02wf58e57","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210131443"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivia Wang","raw_affiliation_strings":["Columbia University, Equal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, Equal","institution_ids":["https://openalex.org/I4210131443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064225886","display_name":"Tiffany Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131443","display_name":"Center for Health and Gender Equity","ror":"https://ror.org/02wf58e57","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210131443"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiffany Zhu","raw_affiliation_strings":["Columbia University, Equal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, Equal","institution_ids":["https://openalex.org/I4210131443"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005107485","display_name":"Tapan Shah","orcid":"https://orcid.org/0000-0003-4481-712X"},"institutions":[{"id":"https://openalex.org/I4210092162","display_name":"General Electric (Israel)","ror":"https://ror.org/00fymn751","country_code":"IL","type":"company","lineage":["https://openalex.org/I1332737386","https://openalex.org/I4210092162"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Tapan Shah","raw_affiliation_strings":["General Electric"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"General Electric","institution_ids":["https://openalex.org/I4210092162"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5043536690"],"corresponding_institution_ids":["https://openalex.org/I4210131443"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03484288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9176999926567078,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9176999926567078,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dither","display_name":"Dither","score":0.7874147891998291},{"id":"https://openalex.org/keywords/rounding","display_name":"Rounding","score":0.7610806226730347},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7071337699890137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6487467288970947},{"id":"https://openalex.org/keywords/learning-vector-quantization","display_name":"Learning vector quantization","score":0.5529718399047852},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.44287109375},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4285432994365692},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4237653911113739},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.4219765365123749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41126835346221924},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40884849429130554},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2747800946235657},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22440531849861145},{"id":"https://openalex.org/keywords/noise-shaping","display_name":"Noise shaping","score":0.12442901730537415}],"concepts":[{"id":"https://openalex.org/C70451592","wikidata":"https://www.wikidata.org/wiki/Q376493","display_name":"Dither","level":3,"score":0.7874147891998291},{"id":"https://openalex.org/C136625980","wikidata":"https://www.wikidata.org/wiki/Q663208","display_name":"Rounding","level":2,"score":0.7610806226730347},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7071337699890137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6487467288970947},{"id":"https://openalex.org/C40567965","wikidata":"https://www.wikidata.org/wiki/Q1820283","display_name":"Learning vector quantization","level":3,"score":0.5529718399047852},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.44287109375},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4285432994365692},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4237653911113739},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.4219765365123749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41126835346221924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40884849429130554},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2747800946235657},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22440531849861145},{"id":"https://openalex.org/C9083635","wikidata":"https://www.wikidata.org/wiki/Q2133535","display_name":"Noise shaping","level":2,"score":0.12442901730537415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.32473/flairs.v34i1.128568","is_oa":true,"landing_page_url":"https://doi.org/10.32473/flairs.v34i1.128568","pdf_url":"https://journals.flvc.org/FLAIRS/article/download/128568/130023","source":{"id":"https://openalex.org/S4210205383","display_name":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","issn_l":"2334-0754","issn":["2334-0754","2334-0762"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310320363","host_organization_name":"George A. Smathers Libraries","host_organization_lineage":["https://openalex.org/P4310320363"],"host_organization_lineage_names":["George A. Smathers Libraries"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International FLAIRS Conference Proceedings","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:87689df6bdbd4592b1b7d45b81f7ba39","is_oa":false,"landing_page_url":"https://doaj.org/article/87689df6bdbd4592b1b7d45b81f7ba39","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"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":"Proceedings of the International Florida Artificial Intelligence Research Society Conference, Vol 34 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.32473/flairs.v34i1.128568","is_oa":true,"landing_page_url":"https://doi.org/10.32473/flairs.v34i1.128568","pdf_url":"https://journals.flvc.org/FLAIRS/article/download/128568/130023","source":{"id":"https://openalex.org/S4210205383","display_name":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","issn_l":"2334-0754","issn":["2334-0754","2334-0762"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310320363","host_organization_name":"George A. Smathers Libraries","host_organization_lineage":["https://openalex.org/P4310320363"],"host_organization_lineage_names":["George A. Smathers Libraries"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International FLAIRS Conference Proceedings","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3162998282.pdf","grobid_xml":"https://content.openalex.org/works/W3162998282.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2100968651","https://openalex.org/W4243803532","https://openalex.org/W1530525041","https://openalex.org/W4244998381","https://openalex.org/W2352648934","https://openalex.org/W4230688072","https://openalex.org/W1915693853","https://openalex.org/W2378212145","https://openalex.org/W2798892016","https://openalex.org/W2202992072"],"abstract_inverted_index":{"With":[0],"advances":[1],"in":[2,5],"edge":[3,25],"applications":[4],"industry":[6],"and":[7,20,32,63,95,123,137,143,156,220],"healthcare,":[8],"machine":[9,41,115],"learning":[10,42,116],"models":[11,43],"are":[12,26,108],"increasingly":[13],"trained":[14,216],"on":[15],"the":[16,24,77,89,106,129,170,195,213,221],"edge.":[17],"However,":[18],"storage":[19],"memory":[21],"infrastructure":[22],"at":[23],"often":[27],"primitive,":[28],"due":[29],"to":[30,39,76,88,96],"cost":[31],"real-estate":[33],"constraints.A":[34],"simple,":[35],"effective":[36],"method":[37],"is":[38,74,86,215,223,237],"learn":[40],"from":[44,70],"quantized":[45,87],"data":[46,219],"stored":[47],"with":[48,92,100,147],"low":[49],"arithmetic":[50],"precision":[51,229,236],"(1-8":[52],"bits).In":[53],"this":[54],"work,":[55],"we":[56,127],"introduce":[57],"two":[58],"stochastic":[59,64,82,138,162],"quantization":[60,136,139,158,163],"methods,":[61],"dithering":[62],"rounding.":[65],"In":[66,81],"dithering,":[67],"additive":[68],"noise":[69],"a":[71,97,133,174,189,199],"uniform":[72],"distribution":[73],"added":[75],"sample":[78,85],"before":[79],"quantization.":[80],"rounding,":[83],"each":[84,226],"upper":[90],"level":[91,99],"probability":[93,101],"p":[94],"lower":[98],"1-p.The":[102],"key":[103],"contributions":[104],"of":[105,176,181],"paper":[107],"as":[109,173],"follows:
":[110],"
":[111,208,242,243],"For":[112],"3":[113],"standard":[114,134,183],"models,":[117],"Support":[118],"Vector":[119],"Machines,":[120],"Decision":[121],"Trees":[122],"Linear":[124],"(Logistic)":[125],"Regression,":[126],"compare":[128],"performance":[130,171],"loss":[131,172],"for":[132,140,154,198,239],"static":[135],"55":[141],"classification":[142],"30":[144],"regression":[145,160],"datasets":[146],"1-8":[148],"bits":[149],"quantization.
":[150],"We":[151,168,202],"showcase":[152],"that":[153],"4-":[155],"8-bit":[157],"over":[159],"datasets,":[161],"demonstrates":[164],"statistically":[165],"significant":[166],"improvement.
":[167],"investigate":[169],"function":[175,191],"dataset":[177],"attributes":[178],"viz.":[179],"number":[180],"features,":[182],"deviation,":[184],"skewness.":[185],"This":[186],"helps":[187],"create":[188],"transfer":[190],"which":[192],"will":[193],"recommend":[194],"best":[196],"quantizer":[197,210,222],"given":[200],"dataset.
":[201],"propose":[203],"2":[204],"future":[205],"research":[206],"areas,
":[207],"dynamic":[209],"update":[211],"where":[212,234],"model":[214],"using":[217],"streaming":[218],"updated":[224],"after":[225],"batch":[227],"and
":[228],"re-allocation":[230],"under":[231],"budget":[232],"constraints":[233],"different":[235,240],"used":[238],"features.
":[241]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}