{"id":"https://openalex.org/W7220970153","doi":"https://doi.org/10.48550/arxiv.2610.09123","title":"Sharp and Adaptive Cluster Recovery in Slowly Mixing Gaussian Hidden Markov Models","display_name":"Sharp and Adaptive Cluster Recovery in Slowly Mixing Gaussian Hidden Markov Models","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7220970153","doi":"https://doi.org/10.48550/arxiv.2610.09123"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.09123","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09123","pdf_url":"https://arxiv.org/pdf/2610.09123","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/2610.09123","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092926085","display_name":"Ibrahim Kaddouri","orcid":"https://orcid.org/0009-0005-6350-6724","observed_orcids":["https://orcid.org/0009-0005-6350-6724"]},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kaddouri, Ibrahim","raw_affiliation_strings":["Department of Statistics , University of Warwick ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics , University of Warwick ,","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091567428","display_name":"Mohamed Ndaoud","orcid":"https://orcid.org/0000-0002-0255-9815","observed_orcids":["https://orcid.org/0000-0002-0255-9815"]},"institutions":[{"id":"https://openalex.org/I124261006","display_name":"\u00c9cole Sup\u00e9rieure des Sciences \u00c9conomiques et Commerciales","ror":"https://ror.org/02dga6j42","country_code":"FR","type":"other","lineage":["https://openalex.org/I124261006"]},{"id":"https://openalex.org/I4405277924","display_name":"ESSEC Business School","ror":"https://ror.org/04be2h179","country_code":"SG","type":"education","lineage":["https://openalex.org/I4405277924"]}],"countries":["FR","SG"],"is_corresponding":false,"raw_author_name":"Ndaoud, Mohamed","raw_affiliation_strings":["Department of Decisions and Operations , ESSEC Business School ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Decisions and Operations , ESSEC Business School ,","institution_ids":["https://openalex.org/I124261006","https://openalex.org/I4405277924"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.8794000148773193,"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":0.8794000148773193,"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/T10136","display_name":"Statistical Methods and Inference","score":0.10249999910593033,"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/T13500","display_name":"Probability and Statistical Research","score":0.0017000000225380063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-recovery","display_name":"cluster recovery","score":0.9229999780654907},{"id":"https://openalex.org/keywords/gaussian-hidden-markov-model","display_name":"Gaussian hidden Markov model","score":0.9430000185966492},{"id":"https://openalex.org/keywords/temporal-persistence","display_name":"temporal persistence","score":0.6549999713897705},{"id":"https://openalex.org/keywords/online-clustering","display_name":"online clustering","score":0.628000020980835},{"id":"https://openalex.org/keywords/minimax-lower-bounds","display_name":"minimax lower bounds","score":0.8519999980926514},{"id":"https://openalex.org/keywords/adaptive-estimation","display_name":"adaptive estimation","score":0.5440000295639038},{"id":"https://openalex.org/keywords/hamming-loss","display_name":"Hamming loss","score":0.7739999890327454}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6679999828338623},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.5748999714851379},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.41620001196861267},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38280001282691956},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C64939953","wikidata":"https://www.wikidata.org/wiki/Q3859882","display_name":"Hidden semi-Markov model","level":5,"score":0.3391000032424927},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.09123","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09123","pdf_url":"https://arxiv.org/pdf/2610.09123","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":"doi:10.48550/arxiv.2610.09123","doi":"https://doi.org/10.48550/arxiv.2610.09123","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.09123","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:2610.09123","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09123","pdf_url":"https://arxiv.org/pdf/2610.09123","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/W7220970153.pdf","grobid_xml":"https://content.openalex.org/works/W7220970153.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2016529189","https://openalex.org/W2074248125","https://openalex.org/W2560270297","https://openalex.org/W2768606360","https://openalex.org/W2942673878","https://openalex.org/W2962736036","https://openalex.org/W3140784025","https://openalex.org/W7116827729"],"related_works":["https://openalex.org/W2942673878","https://openalex.org/W3134305631","https://openalex.org/W4399837307","https://openalex.org/W2884993474","https://openalex.org/W2963763076","https://openalex.org/W7075998540","https://openalex.org/W7170073608","https://openalex.org/W1813234050","https://openalex.org/W2340182652","https://openalex.org/W2121451933"],"abstract_inverted_index":{"We":[0,77,116,167],"study":[1,118],"cluster":[2],"recovery":[3,37,69,182,188,217],"in":[4,11],"a":[5,96,112],"two-state":[6],"Gaussian":[7,43],"hidden":[8],"Markov":[9],"model":[10],"the":[12,17,24,36,41,56,62,84,102,128,139,143,152,157,180,200,204,214,220,230,234,239,247],"slowly":[13],"mixing":[14],"regime,":[15,100],"where":[16],"transition":[18,64,205],"probability":[19,206],"$\u03b4$":[20,207],"may":[21],"vanish":[22],"with":[23,122],"sample":[25,248],"size.":[26],"Temporal":[27],"persistence":[28],"creates":[29],"long":[30],"homogeneous":[31],"segments":[32],"and":[33,90,126,148,172,203,213],"fundamentally":[34],"changes":[35],"problem":[38,153,235],"relative":[39],"to":[40,68,81,198],"i.i.d.":[42],"mixture":[44],"benchmark.":[45],"Rather":[46],"than":[47,245],"being":[48],"purely":[49],"adverse,":[50],"label":[51,124],"dependence":[52],"provides":[53],"exploitable":[54],"structure:":[55],"statistical":[57],"difficulty":[58],"becomes":[59],"concentrated":[60],"near":[61],"rare":[63],"points,":[65],"giving":[66],"rise":[67],"regimes":[70],"governed":[71,155,237],"explicitly":[72],"by":[73,156,238,246],"their":[74],"frequency":[75],"$\u03b4$.":[76],"first":[78,210],"characterize,":[79],"up":[80],"universal":[82],"constants,":[83],"oracle":[85],"Bayes":[86],"risk":[87,99],"for":[88],"offline":[89],"online":[91],"clustering.":[92],"Both":[93],"problems":[94],"exhibit":[95],"nonstandard":[97],"polynomial":[98,176],"but":[101],"sequential":[103],"constraint":[104],"induces":[105],"an":[106],"additional":[107],"logarithmic":[108],"localization":[109],"cost,":[110],"yielding":[111],"genuine":[113],"online/offline":[114],"gap.":[115],"also":[117],"fixed":[119],"lag":[120],"prediction":[121],"delayed":[123],"feedback":[125],"identify":[127],"effective":[129,158,231],"memory":[130],"horizon":[131],"beyond":[132],"which":[133],"past":[134],"labels":[135],"no":[136,209],"longer":[137],"improve":[138],"optimal":[140],"rate.":[141],"When":[142],"signal":[144,159,201],"direction":[145],"is":[146,154,189,223,236],"unknown":[147],"possibly":[149],"high":[150],"dimensional,":[151],"strength":[160],"\\[":[161,224],"r_n^2":[162,225],"=":[163,226],"\\frac{\\|\u03b8\\|^4/\u03c3^4}":[164],"{\\|\u03b8\\|^2/\u03c3^2+d/n}.":[165],"\\]":[166,228],"derive":[168],"minimax":[169],"lower":[170],"bounds":[171],"construct":[173],"fully":[174],"adaptive":[175],"time":[177],"procedures":[178],"attaining":[179],"sharp":[181,215],"rates.":[183],"In":[184],"particular,":[185],"almost":[186],"full":[187],"possible":[190],"precisely":[191],"when":[192],"$r_n^2\\gg\u03b4$.":[193],"If":[194],"$n\u03b4\\gtrsim\\log":[195],"n$,":[196],"adaptation":[197],"both":[199],"$\u03b8$":[202],"incurs":[208],"order":[211],"loss,":[212],"exact":[216],"threshold":[218],"(under":[219],"Hamming":[221],"loss)":[222],"2\\log(n\u03b4)\\,(1+o(1)).":[227],"Thus":[229],"complexity":[232],"of":[233,241],"number":[240],"latent":[242],"transitions,":[243],"rather":[244],"size":[249],"itself.":[250]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}