{"id":"https://openalex.org/W4414359339","doi":"https://doi.org/10.24963/ijcai.2025/531","title":"Dirichlet Process-Based Robust Clustering Using the Median-of-Means Estimator","display_name":"Dirichlet Process-Based Robust Clustering Using the Median-of-Means Estimator","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359339","doi":"https://doi.org/10.24963/ijcai.2025/531"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/531","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5089511169","display_name":"Supratik Basu","orcid":"https://orcid.org/0000-0003-2206-4796"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Supratik Basu","raw_affiliation_strings":["Department of Statistical Science, Duke University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistical Science, Duke University, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044280357","display_name":"Jyotishka Ray Choudhury","orcid":"https://orcid.org/0000-0002-7070-683X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jyotishka Ray Choudhury","raw_affiliation_strings":["H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054854377","display_name":"Debolina Paul","orcid":"https://orcid.org/0000-0002-4106-6685"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Debolina Paul","raw_affiliation_strings":["Machine Learning Research Laboratory, ECSU, Indian Statistical Institute, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Research Laboratory, ECSU, Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000078546","display_name":"Swagatam Das","orcid":"https://orcid.org/0000-0001-6843-4508"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swagatam Das","raw_affiliation_strings":["Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4770","last_page":"4778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9483000040054321,"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":0.9483000040054321,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8033000230789185},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5473999977111816},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.48240000009536743},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4693000018596649},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.4666000008583069},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.4429999887943268},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.423799991607666},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.415800005197525},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.4104999899864197},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.40860000252723694}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8033000230789185},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5529999732971191},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5329999923706055},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.48240000009536743},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4693000018596649},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.4429999887943268},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43779999017715454},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.4104999899864197},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4066999852657318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4023999869823456},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.3702999949455261},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.3472000062465668},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C149872217","wikidata":"https://www.wikidata.org/wiki/Q5265701","display_name":"Determining the number of clusters in a data set","level":5,"score":0.33640000224113464},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33239999413490295},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C115328559","wikidata":"https://www.wikidata.org/wiki/Q4041956","display_name":"k-medians clustering","level":5,"score":0.3230000138282776},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.2939000129699707},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.27630001306533813},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/531","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Clustering":[0],"stands":[1],"as":[2,110],"one":[3],"of":[4,54,104,147,157,162,169,177,191],"the":[5,16,55,65,73,98,102,123,145,155,160,167,189],"most":[6],"prominent":[7],"challenges":[8],"in":[9,64,91,140],"unsupervised":[10],"machine":[11],"learning.":[12],"Among":[13],"centroid-based":[14,83,150],"methods,":[15],"classic":[17],"$k$-means":[18,34],"algorithm,":[19],"based":[20],"on":[21,44,159,173],"Lloyd's":[22],"heuristic,":[23],"is":[24,29,97],"widely":[25],"used.":[26],"Nonetheless,":[27],"it":[28],"a":[30,78,86],"well-known":[31],"fact":[32],"that":[33],"and":[35,58,62,136,149,180,185],"its":[36],"variants":[37],"face":[38],"several":[39],"challenges,":[40],"including":[41],"heavy":[42],"reliance":[43],"initial":[45],"cluster":[46,125],"centroids,":[47],"susceptibility":[48],"to":[49,60,100],"converging":[50],"into":[51],"local":[52],"minima":[53],"objective":[56],"function,":[57],"sensitivity":[59],"outliers":[61],"noise":[63,70,158],"data.":[66],"When":[67],"data":[68],"contains":[69],"or":[71],"outliers,":[72],"Median-of-Means":[74],"(MoM)":[75],"estimator":[76],"offers":[77],"robust":[79],"alternative":[80],"for":[81],"stabilizing":[82],"methods.":[84],"On":[85],"different":[87],"note,":[88],"another":[89],"limitation":[90],"many":[92],"commonly":[93],"used":[94],"clustering":[95,138,163,178,198],"methods":[96],"need":[99],"specify":[101],"number":[103,168],"clusters":[105],"beforehand.":[106],"Model-based":[107],"approaches,":[108],"such":[109],"Bayesian":[111],"nonparametric":[112],"models,":[113,121],"address":[114],"this":[115,141],"issue":[116],"by":[117,129,143],"incorporating":[118],"infinite":[119],"mixture":[120],"eliminating":[122],"predefined":[124],"count":[126],"requirement.":[127],"Motivated":[128],"these":[130],"facts,":[131],"we":[132],"propose":[133],"an":[134,174],"efficient":[135],"automatic":[137],"technique":[139],"article":[142],"integrating":[144],"strengths":[146],"model-based":[148],"methodologies.":[151],"Our":[152],"method":[153,194],"mitigates":[154],"effect":[156],"quality":[161],"while":[164],"simultaneously":[165],"estimating":[166],"clusters.":[170],"Statistical":[171],"guarantees":[172],"upper":[175],"bound":[176],"error":[179],"rigorous":[181],"assessment":[182],"through":[183],"simulated":[184],"real":[186],"datasets":[187],"suggest":[188],"advantages":[190],"our":[192],"proposed":[193],"over":[195],"existing":[196],"state-of-the-art":[197],"algorithms.":[199]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}