{"id":"https://openalex.org/W4411141890","doi":"https://doi.org/10.1145/3725243","title":"Perfect Sampling in Turnstile Streams Beyond Small Moments","display_name":"Perfect Sampling in Turnstile Streams Beyond Small Moments","publication_year":2025,"publication_date":"2025-06-09","ids":{"openalex":"https://openalex.org/W4411141890","doi":"https://doi.org/10.1145/3725243"},"language":"en","primary_location":{"id":"doi:10.1145/3725243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725243","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3725243","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102861589","display_name":"David P. Woodruff","orcid":"https://orcid.org/0000-0002-2158-1380"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David P. Woodruff","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA and Google Research, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2158-1380","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA and Google Research, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117932192","display_name":"Shenghao Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shenghao Xie","raw_affiliation_strings":["Texas A&M University, College Station, USA"],"raw_orcid":"https://orcid.org/0009-0001-8317-9696","affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018283928","display_name":"Samson Zhou","orcid":"https://orcid.org/0000-0001-8288-5698"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samson Zhou","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-8288-5698","affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102861589"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05980464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"2","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9980000257492065,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9980000257492065,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9914000034332275,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9804999828338623,"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/turnstile","display_name":"Turnstile","score":0.9082196950912476},{"id":"https://openalex.org/keywords/streams","display_name":"STREAMS","score":0.7572942972183228},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.622551441192627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.488089919090271},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1493213176727295},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.14772126078605652}],"concepts":[{"id":"https://openalex.org/C31370731","wikidata":"https://www.wikidata.org/wiki/Q7856108","display_name":"Turnstile","level":2,"score":0.9082196950912476},{"id":"https://openalex.org/C42090638","wikidata":"https://www.wikidata.org/wiki/Q4048907","display_name":"STREAMS","level":2,"score":0.7572942972183228},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.622551441192627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.488089919090271},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1493213176727295},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.14772126078605652},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725243","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3725243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725243","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1493892051","https://openalex.org/W1516019649","https://openalex.org/W1546372806","https://openalex.org/W1717978628","https://openalex.org/W1972223681","https://openalex.org/W1979750072","https://openalex.org/W1991099830","https://openalex.org/W2012549717","https://openalex.org/W2031034601","https://openalex.org/W2034417563","https://openalex.org/W2039797405","https://openalex.org/W2045533739","https://openalex.org/W2073479529","https://openalex.org/W2080745194","https://openalex.org/W2107418220","https://openalex.org/W2107917944","https://openalex.org/W2117747231","https://openalex.org/W2119885577","https://openalex.org/W2139076222","https://openalex.org/W2144146806","https://openalex.org/W2160681854","https://openalex.org/W2245672739","https://openalex.org/W2560674852","https://openalex.org/W2595959570","https://openalex.org/W2601261580","https://openalex.org/W2664802502","https://openalex.org/W2730845691","https://openalex.org/W2914354916","https://openalex.org/W2944325705","https://openalex.org/W2963416264","https://openalex.org/W3001954018","https://openalex.org/W3030848490","https://openalex.org/W3031693517","https://openalex.org/W3034414685","https://openalex.org/W3037079313","https://openalex.org/W3102877473","https://openalex.org/W3198744692","https://openalex.org/W4206244036","https://openalex.org/W4210631930","https://openalex.org/W4255005259","https://openalex.org/W4379135613","https://openalex.org/W4396892718","https://openalex.org/W4396893056","https://openalex.org/W4399522983","https://openalex.org/W4404848932","https://openalex.org/W4406141969","https://openalex.org/W4406142101"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2652858764","https://openalex.org/W2024933994","https://openalex.org/W1991681928","https://openalex.org/W2027695577","https://openalex.org/W1869325171","https://openalex.org/W2088907387","https://openalex.org/W1502413331"],"abstract_inverted_index":{"Given":[0],"a":[1,9,14,21,43,65,94,135,184,190,206,215],"vector":[2],"x":[3,100],"\u2208":[4],"\u211d":[5,18],"n":[6,72,88,110],"induced":[7],"by":[8,64],"turnstile":[10,131],"stream":[11,197],"S":[12],",":[13,51],"non-negative":[15],"function":[16,160,165],"G:":[17],"\u2192":[19],"\u211d,":[20],"perfect":[22,44,127,148,155],"G":[23],"-sampler":[24],"outputs":[25],"an":[26,106,172],"index":[27],"i":[28,32,101],"with":[29,102],"probability":[30,104],"G(x":[31],")/\u03a3":[33],"j\u2208[n]":[34],"+":[35],"1/poly(n).":[36],"Jayaram":[37],"and":[38,162],"Woodruff":[39],"(FOCS":[40],"2018)":[41],"introduced":[42],"L":[45,149],"p":[46,50,53,150,167],"-sampler,":[47],"where":[48],"G(z)=|z|":[49],"for":[52,62,157,183,221],"\u2208(0,2].":[54],"In":[55],"this":[56,60],"paper,":[57],"we":[58,119,170],"solve":[59],"problem":[61,179],"p>2":[63],"sampling-and-rejection":[66],"method.":[67],"Our":[68,90],"algorithm":[69,91],"runs":[70],"in":[71,87,143],"1-2/p":[73,111],"\u2022":[74,112],"polylog":[75,113],"(n)":[76,114],"bits":[77,115],"of":[78,116,137,174,180,187,189,217],"space,":[79],"which":[80,133],"is":[81,134,140,198],"tight":[82],"up":[83],"to":[84,96,126,145,177,224],"polylogarithmic":[85],"factors":[86],".":[89],"also":[92,153],"provides":[93],"(1+\u03b5)-approximation":[95],"the":[97,146,158,163,178,195,202,210,228],"sampled":[98],"item":[99],"high":[103],"using":[105],"additional":[107],"\u03b5":[108],"-2":[109],"space.":[117],"Interestingly,":[118],"show":[120],"our":[121,175],"techniques":[122],"can":[123],"be":[124,225],"generalized":[125],"polynomial":[128],"samplers":[129,156],"on":[130],"streams,":[132],"class":[136],"functions":[138],"that":[139],"not":[141],"scale-invariant,":[142],"contrast":[144],"existing":[147],"samplers.":[151],"We":[152],"achieve":[154],"logarithmic":[159],"G(z)=log(1+|z|)":[161],"cap":[164],"G(z)=min(T,|z|":[166],").":[168],"Finally,":[169],"give":[171],"application":[173],"results":[176],"norm/moment":[181],"estimation":[182],"subset":[185],"Q":[186,204,213],"coordinates":[188],"vector,":[191],"revealed":[192],"only":[193],"after":[194],"data":[196],"processed,":[199],"e.g.,":[200],"when":[201],"set":[203,211],"represents":[205,214],"range":[207],"query,":[208],"or":[209],"n\\":[212],"collection":[216],"entities":[218],"who":[219],"wish":[220],"their":[222],"information":[223],"expunged":[226],"from":[227],"dataset.":[229]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}