{"id":"https://openalex.org/W2164573470","doi":null,"title":"Coresets for Nonparametric Estimation \u2014 the Case of DP-Means","display_name":"Coresets for Nonparametric Estimation \u2014 the Case of DP-Means","publication_year":2016,"publication_date":"2016-10-20","ids":{"openalex":"https://openalex.org/W2164573470","mag":"2164573470"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1010.6171","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1010.6171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://machinelearning.wustl.edu/mlpapers/paper_files/icml2015_bachem15.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089890773","display_name":"Olivier Bachem","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Olivier Bachem","raw_affiliation_strings":["ETH Zurich, SWITZERLAND"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, SWITZERLAND","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044677020","display_name":"Mario Lu\u010di\u0107","orcid":"https://orcid.org/0009-0000-7826-2340","observed_orcids":["https://orcid.org/0009-0000-7826-2340"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mario Lucic","raw_affiliation_strings":["ETH Zurich, SWITZERLAND"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, SWITZERLAND","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003040843","display_name":"Andreas Krause","orcid":"https://orcid.org/0000-0001-7260-9673","observed_orcids":["https://orcid.org/0000-0001-7260-9673"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Krause","raw_affiliation_strings":["ETH Zurich, SWITZERLAND"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich, SWITZERLAND","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":6.4221,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.96876172,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.6288999915122986,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.6288999915122986,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.1543000042438507,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.03959999978542328,"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/coresets","display_name":"coresets","score":0.9909999966621399},{"id":"https://openalex.org/keywords/bayesian-nonparametric-models","display_name":"Bayesian nonparametric models","score":0.8190000057220459},{"id":"https://openalex.org/keywords/nonparametric-clustering","display_name":"nonparametric clustering","score":0.875},{"id":"https://openalex.org/keywords/data-summarization","display_name":"data summarization","score":0.8059999942779541},{"id":"https://openalex.org/keywords/scalable-inference","display_name":"scalable inference","score":0.6430000066757202},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"approximate inference","score":0.6840000152587891},{"id":"https://openalex.org/keywords/coreset-construction","display_name":"coreset construction","score":0.5630000233650208},{"id":"https://openalex.org/keywords/subsampling","display_name":"subsampling","score":0.5669999718666077},{"id":"https://openalex.org/keywords/approximation-error","display_name":"approximation error","score":0.6110000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707598865032196},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5696235299110413},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5647530555725098},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5519301295280457},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4449227452278137},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.44233182072639465},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44138801097869873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31376177072525024},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23955082893371582},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1110122799873352},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1010.6171","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1010.6171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://machinelearning.wustl.edu/mlpapers/paper_files/icml2015_bachem15.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1540484164","https://openalex.org/W1556219185","https://openalex.org/W1967687583","https://openalex.org/W1974600023","https://openalex.org/W1977983731","https://openalex.org/W1981773323","https://openalex.org/W2045964207","https://openalex.org/W2053405531","https://openalex.org/W2061902728","https://openalex.org/W2073459066","https://openalex.org/W2080972498","https://openalex.org/W2091797506","https://openalex.org/W2094048240","https://openalex.org/W2101012814","https://openalex.org/W2112796928","https://openalex.org/W2127498532","https://openalex.org/W2130510032","https://openalex.org/W2143776582","https://openalex.org/W2146200992","https://openalex.org/W2162469599","https://openalex.org/W2171125141"],"related_works":["https://openalex.org/W2593346713","https://openalex.org/W2146200992","https://openalex.org/W4221148775","https://openalex.org/W3112617506","https://openalex.org/W4401103849","https://openalex.org/W4407385275","https://openalex.org/W2953116466","https://openalex.org/W2612467436","https://openalex.org/W3039945744","https://openalex.org/W4412334830"],"abstract_inverted_index":{"Scalable":[0],"training":[1],"of":[2,15,34,86,137,144,167,176],"Bayesian":[3],"nonparametric":[4,93],"models":[5,39,48],"is":[6],"a":[7,18,91,99,134],"notoriously":[8],"difficult":[9],"challenge.":[10],"We":[11,103],"explore":[12],"the":[13,35,51,57,84,152,159,163,170],"use":[14],"coresets":[16,43,87,130],"\u2013":[17,26,90,96],"data":[19,36,154,171],"summariza-tion":[20],"technique":[21],"originating":[22],"from":[23],"computational":[24,135],"geometry":[25],"for":[27,61,88,158],"this":[28],"task.":[29],"Coresets":[30,54],"are":[31,44,71],"weighted":[32],"subsets":[33],"such":[37],"that":[38,106],"trained":[40,49],"on":[41,50,151],"these":[42],"provably":[45],"competitive":[46],"with":[47,65,129],"full":[52,153],"dataset.":[53],"sublinear":[55],"in":[56,79],"dataset":[58],"size":[59],"allow":[60],"fast":[62],"approximate":[63],"inference":[64],"provable":[66],"guarantees.":[67],"Existing":[68],"constructions,":[69],"however,":[70],"limited":[72],"to":[73,111,124,149],"parametric":[74],"problems.":[75],"Using":[76],"novel":[77],"techniques":[78],"coreset":[80],"construction":[81,101],"we":[82,131],"show":[83],"existence":[85],"DP-Means":[89,123],"prototypical":[92],"clustering":[94],"problem":[95],"and":[97,117,120],"provide":[98],"practical":[100],"algorithm.":[102],"empiri-cally":[104],"demonstrate":[105],"our":[107],"algorithm":[108],"allows":[109],"us":[110],"efficiently":[112],"trade":[113],"off":[114],"computation":[115],"time":[116],"approximation":[118,142,174],"error":[119,143,175],"thus":[121],"scale":[122],"large":[125],"datasets.":[126],"For":[127],"instance,":[128],"can":[132],"obtain":[133],"speedup":[136],"45":[138],"\u00d7":[139],"at":[140],"an":[141,173],"only":[145],"2.4":[146],"%":[147],"compared":[148],"solving":[150],"set.":[155],"In":[156],"contrast,":[157],"same":[160],"subsample":[161],"size,":[162],"\u201cnaive":[164],"\u201d":[165],"approach":[166],"uniformly":[168],"subsampling":[169],"incurs":[172],"22.5%.":[177],"1.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}