{"id":"https://openalex.org/W7223335637","doi":"https://doi.org/10.48550/arxiv.2610.31431","title":"Dimension-free regimes for unadjusted Langevin in ridge-separable models: A subspace robust Wasserstein analysis","display_name":"Dimension-free regimes for unadjusted Langevin in ridge-separable models: A subspace robust Wasserstein analysis","publication_year":2026,"publication_date":"2026-10-22","ids":{"openalex":"https://openalex.org/W7223335637","doi":"https://doi.org/10.48550/arxiv.2610.31431"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.31431","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.31431","pdf_url":"https://arxiv.org/pdf/2610.31431","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/2610.31431","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159302214","display_name":"Yuansi Chen","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"]},{"id":"https://openalex.org/I4405257864","display_name":"Seminar for Statistics","ror":"https://ror.org/05rkrf147","country_code":"CH","type":"facility","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088","https://openalex.org/I4405257864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Chen, Yuansi","raw_affiliation_strings":["Seminar for Statistics , ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seminar for Statistics , ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088","https://openalex.org/I4405257864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008315500","display_name":"Francesco Pedrotti","orcid":"https://orcid.org/0009-0002-8099-2611","observed_orcids":["https://orcid.org/0009-0002-8099-2611"]},"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"]},{"id":"https://openalex.org/I4405257864","display_name":"Seminar for Statistics","ror":"https://ror.org/05rkrf147","country_code":"CH","type":"facility","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088","https://openalex.org/I4405257864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Pedrotti, Francesco","raw_affiliation_strings":["Seminar for Statistics , ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seminar for Statistics , ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088","https://openalex.org/I4405257864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091801645","display_name":"Peter A. Whalley","orcid":"https://orcid.org/0000-0002-8360-0807","observed_orcids":["https://orcid.org/0000-0002-8360-0807"]},"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":"Whalley, Peter A.","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"]}]}],"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":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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9990000128746033,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9990000128746033,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.0003000000142492354,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.00019999999494757503,"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/unadjusted-langevin-algorithm","display_name":"unadjusted Langevin algorithm","score":0.9810000061988831},{"id":"https://openalex.org/keywords/mixing-time","display_name":"mixing time","score":0.675000011920929},{"id":"https://openalex.org/keywords/asymptotic-bias","display_name":"asymptotic bias","score":0.8989999890327454},{"id":"https://openalex.org/keywords/high-dimensional-bayesian-inference","display_name":"high-dimensional Bayesian inference","score":0.796999990940094},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.7440000176429749},{"id":"https://openalex.org/keywords/gaussian-perturbation","display_name":"Gaussian perturbation","score":0.6000000238418579},{"id":"https://openalex.org/keywords/effective-dimension","display_name":"effective dimension","score":0.48899999260902405}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.760200023651123},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.6812000274658203},{"id":"https://openalex.org/C2777634741","wikidata":"https://www.wikidata.org/wiki/Q768993","display_name":"Wasserstein metric","level":2,"score":0.6793000102043152},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6626999974250793},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6166999936103821},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5648000240325928},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4397999942302704},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.36500000953674316},{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C21031990","wikidata":"https://www.wikidata.org/wiki/Q355020","display_name":"Probability measure","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C30732413","wikidata":"https://www.wikidata.org/wiki/Q17092636","display_name":"Intrinsic dimension","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C115311070","wikidata":"https://www.wikidata.org/wiki/Q5347255","display_name":"Effective dimension","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.31431","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.31431","pdf_url":"https://arxiv.org/pdf/2610.31431","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.2610.31431","doi":"https://doi.org/10.48550/arxiv.2610.31431","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.31431","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:2610.31431","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.31431","pdf_url":"https://arxiv.org/pdf/2610.31431","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":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223335637.pdf","grobid_xml":"https://content.openalex.org/works/W7223335637.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W4293782201","https://openalex.org/W4364387748","https://openalex.org/W4389116445","https://openalex.org/W4405434018","https://openalex.org/W4410384987","https://openalex.org/W4415953526","https://openalex.org/W4417070581","https://openalex.org/W4417451803","https://openalex.org/W7162133892","https://openalex.org/W7172404554"],"related_works":["https://openalex.org/W7172404554","https://openalex.org/W7126273032","https://openalex.org/W4302578562","https://openalex.org/W2948375734","https://openalex.org/W7133532547","https://openalex.org/W7172516400","https://openalex.org/W2626226418","https://openalex.org/W7077483628","https://openalex.org/W2962794482","https://openalex.org/W4402630168"],"abstract_inverted_index":{"The":[0],"Unadjusted":[1],"Langevin":[2],"Algorithm":[3],"(ULA)":[4],"is":[5,32,59,105,133],"widely":[6],"used":[7],"for":[8,36],"high-dimensional":[9],"Bayesian":[10],"inference.":[11],"Classical":[12],"analyses":[13],"in":[14,45,67,151],"Wasserstein-2":[15],"distance":[16],"predict":[17],"an":[18],"asymptotic":[19],"bias":[20,44],"and":[21,54,58],"a":[22,81],"mixing":[23,83],"time":[24],"that":[25,146],"grow":[26],"with":[27,73],"dimension,":[28],"but":[29],"this":[30],"metric":[31],"stronger":[33],"than":[34,120],"necessary":[35],"many":[37],"statistical":[38],"tasks.":[39],"We":[40],"instead":[41],"analyze":[42],"the":[43,52,86,95,99,102,106,110,123,139],"subspace":[46],"robust":[47],"Wasserstein":[48],"distance,":[49],"which":[50],"controls":[51],"mean":[53],"arbitrary":[55],"low-dimensional":[56],"marginals":[57],"therefore":[60],"well":[61],"suited":[62],"to":[63,94,114],"observables":[64],"typically":[65],"estimated":[66],"practice.":[68],"For":[69],"ridge-separable":[70],"potentials":[71],"formed":[72],"i.i.d.":[74],"data,":[75],"we":[76,144],"prove":[77,145],"high-probability":[78],"bounds":[79],"showing":[80],"bell-shaped":[82],"profile":[84],"as":[85],"number":[87],"of":[88,109],"data":[89],"points":[90],"$N$":[91,108,118,132],"varies":[92],"relative":[93],"dimension":[96,104],"$d$.":[97,121],"In":[98,122,136],"overparameterized":[100],"regime,":[101,125],"effective":[103],"rank":[107],"data-dependent":[111],"perturbation,":[112],"leading":[113],"complexity":[115,130],"depending":[116],"on":[117],"rather":[119],"large-sample":[124],"Gaussian-perturbation":[126],"estimates":[127],"yield":[128],"dimension-free":[129,147],"once":[131],"sufficiently":[134],"large.":[135],"contrast,":[137],"near":[138],"proportional":[140],"regime":[141],"$\\asymp":[142],"d$,":[143],"guarantees":[148],"are":[149],"impossible":[150],"general.":[152]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-24T00:00:00"}