{"id":"https://openalex.org/W7171381160","doi":"https://doi.org/10.48550/arxiv.2607.22063","title":"HyperLogLog for probabilists","display_name":"HyperLogLog for probabilists","publication_year":2026,"publication_date":"2026-07-24","ids":{"openalex":"https://openalex.org/W7171381160","doi":"https://doi.org/10.48550/arxiv.2607.22063"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2607.22063","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.22063","pdf_url":"https://arxiv.org/pdf/2607.22063","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.22063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021547605","display_name":"Lucas Gerin","orcid":"https://orcid.org/0000-0003-2634-3258","observed_orcids":["https://orcid.org/0000-0003-2634-3258"]},"institutions":[{"id":"https://openalex.org/I4387155343","display_name":"Mod\u00e9lisation al\u00e9atoire de Paris Nanterre","ror":"https://ror.org/00cjjmc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I40434647","https://openalex.org/I4387155343"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Gerin, Lucas","raw_affiliation_strings":["MODAL'X"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MODAL'X","institution_ids":["https://openalex.org/I4387155343"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5021547605"],"corresponding_institution_ids":["https://openalex.org/I4387155343"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T13500","display_name":"Probability and Statistical Research","score":0.5479000210762024,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13500","display_name":"Probability and Statistical Research","score":0.5479000210762024,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.1851000040769577,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.03689999878406525,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/hyperloglog","display_name":"HyperLogLog","score":0.9950000047683716},{"id":"https://openalex.org/keywords/cardinality-estimation","display_name":"cardinality estimation","score":0.906000018119812},{"id":"https://openalex.org/keywords/distinct-elements","display_name":"distinct elements","score":0.6909999847412109},{"id":"https://openalex.org/keywords/probabilistic-data-structures","display_name":"probabilistic data structures","score":0.7250000238418579},{"id":"https://openalex.org/keywords/deviation-inequalities","display_name":"deviation inequalities","score":0.5699999928474426},{"id":"https://openalex.org/keywords/nonasymptotic-bounds","display_name":"non-asymptotic bounds","score":0.8560000061988831},{"id":"https://openalex.org/keywords/expectation-and-variance","display_name":"expectation and variance","score":0.6589999794960022},{"id":"https://openalex.org/keywords/poissonization","display_name":"Poissonization","score":0.7310000061988831},{"id":"https://openalex.org/keywords/mellin-transform","display_name":"Mellin transform","score":0.8610000014305115},{"id":"https://openalex.org/keywords/one-pass-algorithms","display_name":"one-pass algorithms","score":0.4230000078678131}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6638000011444092},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6080999970436096},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.41909998655319214},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2777686260","wikidata":"https://www.wikidata.org/wiki/Q144037","display_name":"Calculus (dental)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.32109999656677246},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C122203268","wikidata":"https://www.wikidata.org/wiki/Q5862903","display_name":"Probability theory","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2728999853134155},{"id":"https://openalex.org/C75438885","wikidata":"https://www.wikidata.org/wiki/Q3403615","display_name":"Large deviations theory","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C60782215","wikidata":"https://www.wikidata.org/wiki/Q3333679","display_name":"Probabilistic method","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C24404364","wikidata":"https://www.wikidata.org/wiki/Q7246846","display_name":"Probabilistic analysis of algorithms","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C55350006","wikidata":"https://www.wikidata.org/wiki/Q237193","display_name":"Exponential distribution","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2607.22063","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.22063","pdf_url":"https://arxiv.org/pdf/2607.22063","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,"listed_in":[],"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:HAL:hal-05702505v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05702505","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2026","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:HAL:hal-05702505v2","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05702505","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2026","raw_type":"info:eu-repo/semantics/preprint"},{"id":"doi:10.48550/arxiv.2607.22063","doi":"https://doi.org/10.48550/arxiv.2607.22063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.22063","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.22063","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.22063","pdf_url":"https://arxiv.org/pdf/2607.22063","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7171381160.pdf","grobid_xml":"https://content.openalex.org/works/W7171381160.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2593397259","https://openalex.org/W2904955837"],"related_works":["https://openalex.org/W2144982963","https://openalex.org/W2593397259","https://openalex.org/W4412453335","https://openalex.org/W3166698353","https://openalex.org/W2719363210","https://openalex.org/W3054334137","https://openalex.org/W3176074410","https://openalex.org/W2561669610","https://openalex.org/W4293253645","https://openalex.org/W7147154730"],"abstract_inverted_index":{"HyperLogLog":[0,67,83],"is":[1],"a":[2,18,38,69],"now":[3],"classic":[4],"probabilistic":[5,71],"algorithm":[6],"that":[7],"provides":[8],"an":[9],"approximation":[10],"of":[11,14,41,46,66],"the":[12,26,29,42,47,64,82,90],"number":[13],"distinct":[15],"elements":[16],"in":[17],"massive":[19],"dataset,":[20],"using":[21,49,53],"only":[22],"one":[23],"pass":[24],"over":[25],"data.":[27],"In":[28,58],"original":[30],"article,":[31,61],"Flajolet,":[32],"Fusy,":[33],"Gandouet,":[34],"Meunier":[35],"(2007)":[36],"provided":[37],"sharp":[39],"analysis":[40,65],"expectation":[43],"and":[44,55,94],"variance":[45],"output,":[48],"explicit":[50],"formulas":[51],"analyzed":[52],"poissonization":[54],"Mellin":[56],"transform.":[57],"this":[59],"short":[60],"we":[62],"revisit":[63],"with":[68],"more":[70],"viewpoint.":[72],"This":[73],"allows":[74],"us":[75],"to":[76],"establish":[77],"exponential":[78],"deviation":[79],"inequalities":[80],"for":[81],"estimator.":[84],"The":[85],"methods":[86],"are":[87,92],"elementary,":[88],"but":[89],"estimates":[91],"non-asymptotic":[93],"totally":[95],"explicit.":[96]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-07-28T00:00:00"}