{"id":"https://openalex.org/W4289647228","doi":"https://doi.org/10.48550/arxiv.2102.09101","title":"Online $k$-means Clustering on Arbitrary Data Streams","display_name":"Online $k$-means Clustering on Arbitrary Data Streams","publication_year":2021,"publication_date":"2021-02-18","ids":{"openalex":"https://openalex.org/W4289647228","doi":"https://doi.org/10.48550/arxiv.2102.09101"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2102.09101","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.09101","pdf_url":"https://arxiv.org/pdf/2102.09101","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2102.09101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010685516","display_name":"Robi Bhattacharjee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhattacharjee, Robi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007061557","display_name":"Jacob Imola","orcid":"https://orcid.org/0009-0002-0367-509X","observed_orcids":["https://orcid.org/0009-0002-0367-509X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Imola, Jacob","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025544885","display_name":"Michal Moshkovitz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moshkovitz, Michal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101707744","display_name":"Sanjoy Dasgupta","orcid":"https://orcid.org/0000-0002-5960-5157","observed_orcids":["https://orcid.org/0000-0002-5960-5157"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dasgupta, Sanjoy","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":true,"cited_by_count":2,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.95169997215271,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.95169997215271,"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":0.026000000536441803,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.003100000089034438,"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/data-streams","display_name":"data streams","score":0.9549999833106995},{"id":"https://openalex.org/keywords/streaming-algorithms","display_name":"streaming algorithms","score":0.5239999890327454},{"id":"https://openalex.org/keywords/randomized-algorithms","display_name":"randomized algorithms","score":0.5440000295639038},{"id":"https://openalex.org/keywords/approximation-guarantees","display_name":"approximation guarantees","score":0.6439999938011169},{"id":"https://openalex.org/keywords/cluster-centers","display_name":"cluster centers","score":0.6190000176429749},{"id":"https://openalex.org/keywords/space-complexity","display_name":"space complexity","score":0.6620000004768372},{"id":"https://openalex.org/keywords/loss-reduction","display_name":"loss reduction","score":0.47999998927116394},{"id":"https://openalex.org/keywords/lower-bounds","display_name":"lower bounds","score":0.4020000100135803}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6748566627502441},{"id":"https://openalex.org/C2779557605","wikidata":"https://www.wikidata.org/wiki/Q9890","display_name":"Omega","level":2,"score":0.6480981707572937},{"id":"https://openalex.org/C63553672","wikidata":"https://www.wikidata.org/wiki/Q581168","display_name":"Binary logarithm","level":2,"score":0.6334314942359924},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.5835922956466675},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5578612685203552},{"id":"https://openalex.org/C2778113609","wikidata":"https://www.wikidata.org/wiki/Q10897","display_name":"Lambda","level":2,"score":0.5363928079605103},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.5299404859542847},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.4964213967323303},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.45685887336730957},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.43717458844184875},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.39885246753692627},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3922240734100342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3629661202430725},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35176151990890503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2025158703327179},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1799616813659668},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14691680669784546},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"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/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2102.09101","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.09101","pdf_url":"https://arxiv.org/pdf/2102.09101","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2102.09101","doi":"https://doi.org/10.48550/arxiv.2102.09101","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.09101","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.09101","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.09101","pdf_url":"https://arxiv.org/pdf/2102.09101","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4289647228.pdf","grobid_xml":"https://content.openalex.org/works/W4289647228.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W3172712527"],"related_works":["https://openalex.org/W4390098035","https://openalex.org/W2100369465","https://openalex.org/W4244622952","https://openalex.org/W7097643466","https://openalex.org/W7095518988","https://openalex.org/W2185540342","https://openalex.org/W4242711918","https://openalex.org/W2963798749","https://openalex.org/W1965456679","https://openalex.org/W2156499390"],"abstract_inverted_index":{"We":[0,70,102],"consider":[1],"online":[2],"$k$-means":[3],"clustering":[4,110],"where":[5],"each":[6],"new":[7,34],"point":[8],"is":[9,27,48,53,100,139,155],"assigned":[10,38],"to":[11,36,49,143,158],"the":[12,18,28,60,140,156,167],"nearest":[13],"cluster":[14,39,126],"center,":[15],"after":[16],"which":[17,95],"algorithm":[19,80,107,117,129,142],"may":[20],"update":[21],"its":[22],"centers.":[23,40,127],"The":[24,41],"loss":[25,51,63,97,111],"incurred":[26],"sum":[29],"of":[30,57,98,135],"squared":[31],"distances":[32],"from":[33],"points":[35,67],"their":[37],"goal":[42],"over":[43],"a":[44,54,72,90,96,105,132],"data":[45,73,91],"stream":[46,92],"$X$":[47,93],"achieve":[50,144],"that":[52,77,108],"constant":[55],"factor":[56],"$L(X,":[58],"OPT_k)$,":[59],"best":[61],"possible":[62],"using":[64],"$k$":[65],"fixed":[66],"in":[68,150],"hindsight.":[69],"propose":[71],"parameter,":[74],"$\u039b(X)$,":[75],"such":[76],"for":[78,94],"any":[79,164],"maintaining":[81],"$O(k\\text{poly}(\\log":[82,119,124,136],"n))$":[83,120,125,137],"centers":[84],"at":[85],"time":[86,134,148],"$n$,":[87],"there":[88],"exists":[89],"$\u03a9(\u039b(X))$":[99],"inevitable.":[101],"then":[103],"give":[104],"randomized":[106],"achieves":[109],"$O(\u039b(X)":[112],"+":[113],"L(X,":[114],"OPT_k))$.":[115],"Our":[116,128],"uses":[118],"memory":[121],"and":[122,138,147],"maintains":[123],"also":[130,154],"enjoys":[131],"running":[133],"first":[141,157],"polynomial":[145],"space":[146],"complexity":[149],"this":[151],"setting.":[152],"It":[153],"have":[159],"provable":[160],"guarantees":[161],"without":[162],"making":[163],"assumptions":[165],"on":[166],"input":[168],"data.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-08-03T00:00:00"}