{"id":"https://openalex.org/W7118007219","doi":"https://doi.org/10.48550/arxiv.2512.24515","title":"Improving the stability of the covariance-controlled adaptive Langevin thermostat for large-scale Bayesian sampling","display_name":"Improving the stability of the covariance-controlled adaptive Langevin thermostat for large-scale Bayesian sampling","publication_year":2025,"publication_date":"2025-12-30","ids":{"openalex":"https://openalex.org/W7118007219","doi":"https://doi.org/10.48550/arxiv.2512.24515"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.24515","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.24515","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2512.24515","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121781993","display_name":"Jiani Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Jiani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078193828","display_name":"Xiaocheng Shang","orcid":"https://orcid.org/0000-0001-8376-6498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang, Xiaocheng","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":false,"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":0.9014000296592712,"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":0.9014000296592712,"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":0.049300000071525574,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.012299999594688416,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/stability","display_name":"Stability (learning theory)","score":0.5400999784469604},{"id":"https://openalex.org/keywords/thermostat","display_name":"Thermostat","score":0.4668000042438507},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.446399986743927},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.43709999322891235},{"id":"https://openalex.org/keywords/langevin-dynamics","display_name":"Langevin dynamics","score":0.4341000020503998},{"id":"https://openalex.org/keywords/numerical-stability","display_name":"Numerical stability","score":0.4115999937057495},{"id":"https://openalex.org/keywords/matrix-exponential","display_name":"Matrix exponential","score":0.41100001335144043},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4009000062942505}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.550000011920929},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5169000029563904},{"id":"https://openalex.org/C187819001","wikidata":"https://www.wikidata.org/wiki/Q187665","display_name":"Thermostat","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C176321772","wikidata":"https://www.wikidata.org/wiki/Q1430640","display_name":"Numerical stability","level":3,"score":0.4115999937057495},{"id":"https://openalex.org/C195906000","wikidata":"https://www.wikidata.org/wiki/Q1191722","display_name":"Matrix exponential","level":3,"score":0.41100001335144043},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C158946198","wikidata":"https://www.wikidata.org/wiki/Q131187","display_name":"Taylor series","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3231000006198883},{"id":"https://openalex.org/C48753275","wikidata":"https://www.wikidata.org/wiki/Q11216","display_name":"Numerical analysis","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.2953000068664551},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26440000534057617}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.24515","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.24515","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2512.24515","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.24515","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,"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"},"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":{"Stochastic":[0],"gradient":[1,234],"Langevin":[2,56],"dynamics":[3],"and":[4,154],"its":[5],"variants":[6],"approximate":[7,169],"the":[8,22,29,34,52,65,69,85,89,95,115,123,126,131,148,152,165,170,174,177,199,210,220,224,239],"likelihood":[9],"of":[10,24,33,68,88,117,125,151,193,238],"an":[11,61,194],"entire":[12],"dataset,":[13],"via":[14],"random":[15],"(and":[16],"typically":[17],"much":[18],"smaller)":[19],"subsets,":[20],"in":[21,42,81,92,104,110,181,198,205,219,236],"setting":[23],"Bayesian":[25],"sampling.":[26],"Due":[27],"to":[28,83,100,164,167,173],"(often":[30],"substantial)":[31],"improvement":[32,218],"computational":[35],"efficiency,":[36],"they":[37],"have":[38],"been":[39,49],"widely":[40],"used":[41,80,197],"large-scale":[43,243],"machine":[44,244],"learning":[45,245],"applications.":[46,246],"It":[47],"has":[48],"demonstrated":[50],"that":[51,114,146,209],"so-called":[53],"covariance-controlled":[54],"adaptive":[55],"(CCAdL)":[57],"thermostat,":[58,227],"which":[59,93],"incorporates":[60],"additional":[62,178],"term":[63,179],"involving":[64,176],"covariance":[66,86,96],"matrix":[67,87,97,103],"noisy":[70,90],"force,":[71,91],"outperforms":[72],"popular":[73,231],"alternative":[74,232],"methods.":[75],"A":[76],"moving":[77,119],"average":[78,120],"is":[79],"CCAdL":[82,142,201,226],"estimate":[84],"case":[94],"will":[98],"converge":[99],"a":[101,118,140,159,186,216],"constant":[102],"long-time":[105],"limit.":[106],"Moreover,":[107],"it":[108],"appears":[109],"our":[111,206],"numerical":[112,127,207,221,240],"experiments":[113,208],"use":[116],"could":[121],"reduce":[122],"stability":[124,222],"integrators,":[128],"thereby":[129],"limiting":[130],"largest":[132],"usable":[133],"stepsize.":[134],"In":[135],"this":[136],"article,":[137],"we":[138],"propose":[139,185],"modified":[141],"(i.e.,":[143],"mCCAdL)":[144],"thermostat":[145,214],"uses":[147],"scaling":[149,153],"part":[150],"squaring":[155],"method":[156,189],"together":[157],"with":[158],"truncated":[160],"Taylor":[161],"series":[162],"approximation":[163],"exponential":[166],"numerically":[168],"exact":[171],"solution":[172],"subsystem":[175],"proposed":[180,212],"CCAdL.":[182],"We":[183,203],"also":[184],"symmetric":[187],"splitting":[188],"for":[190,242],"mCCAdL,":[191],"instead":[192],"Euler-type":[195],"discretisation":[196],"original":[200,225],"thermostat.":[202],"demonstrate":[204],"newly":[211],"mCCAdL":[213],"achieves":[215],"substantial":[217],"over":[223],"while":[228],"significantly":[229],"outperforming":[230],"stochastic":[233],"methods":[235],"terms":[237],"accuracy":[241]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-01-02T00:00:00"}