{"id":"https://openalex.org/W7213606609","doi":"https://doi.org/10.48550/arxiv.2609.20713","title":"A Unified Framework for Wasserstein Convergence of ULMC Methods beyond Log-Concavity: Old and New","display_name":"A Unified Framework for Wasserstein Convergence of ULMC Methods beyond Log-Concavity: Old and New","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213606609","doi":"https://doi.org/10.48550/arxiv.2609.20713"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.20713","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20713","pdf_url":"https://arxiv.org/pdf/2609.20713","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/2609.20713","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152144592","display_name":"Wanjie Lyu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lyu, Wanjie","raw_affiliation_strings":["School of Mathematics and Statistics , HNP-LAMA , Central South University , Changsha , 410083 , Hunan , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics , HNP-LAMA , Central South University , Changsha , 410083 , Hunan , China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126158429","display_name":"Xiaojie Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Xiaojie","raw_affiliation_strings":["School of Mathematics and Statistics , HNP-LAMA , Central South University , Changsha , 410083 , Hunan , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics , HNP-LAMA , Central South University , Changsha , 410083 , Hunan , China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5152146927","display_name":"Bin Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Bin","raw_affiliation_strings":["School of Mathematics and Statistics , HNP-LAMA , Central South University , Changsha , 410083 , Hunan , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics , HNP-LAMA , Central South University , Changsha , 410083 , Hunan , China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139660479"],"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":0.9984999895095825,"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":0.9984999895095825,"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/T11416","display_name":"Numerical Solvers for Ordinary Differential Equations","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":9.999999747378752e-05,"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/underdamped-langevin-dynamics","display_name":"underdamped Langevin dynamics","score":0.9819999933242798},{"id":"https://openalex.org/keywords/predictor-corrector-method","display_name":"predictor-corrector method","score":0.8090000152587891},{"id":"https://openalex.org/keywords/high-dimensional-sampling","display_name":"high-dimensional sampling","score":0.7689999938011169},{"id":"https://openalex.org/keywords/non-asymptotic-error-bounds","display_name":"non-asymptotic error bounds","score":0.9169999957084656},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.48100000619888306}],"concepts":[{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.6366999745368958},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5874000191688538},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5364000201225281},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C79518650","wikidata":"https://www.wikidata.org/wiki/Q2081431","display_name":"Integrator","level":3,"score":0.498199999332428},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C21031990","wikidata":"https://www.wikidata.org/wiki/Q355020","display_name":"Probability measure","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39480000734329224},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.38339999318122864},{"id":"https://openalex.org/C104824951","wikidata":"https://www.wikidata.org/wiki/Q830124","display_name":"Girsanov theorem","level":3,"score":0.375},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.32420000433921814},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.31209999322891235},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3084999918937683},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C128669082","wikidata":"https://www.wikidata.org/wiki/Q583461","display_name":"Randomized algorithm","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26190000772476196}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.20713","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20713","pdf_url":"https://arxiv.org/pdf/2609.20713","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.2609.20713","doi":"https://doi.org/10.48550/arxiv.2609.20713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.20713","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.20713","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20713","pdf_url":"https://arxiv.org/pdf/2609.20713","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":[{"id":"https://openalex.org/G1983837051","display_name":null,"funder_award_id":"12471394","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6849372555","display_name":null,"funder_award_id":"12371417","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320311213","display_name":"Education Department of Hunan Province","ror":"https://ror.org/05ckg3w11"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213606609.pdf","grobid_xml":"https://content.openalex.org/works/W7213606609.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4397028397","https://openalex.org/W7084116200","https://openalex.org/W7164036005"],"related_works":["https://openalex.org/W7077483628","https://openalex.org/W4321276783","https://openalex.org/W7133532547","https://openalex.org/W3159440435","https://openalex.org/W4397028397","https://openalex.org/W7160862205","https://openalex.org/W2736302961","https://openalex.org/W2951787821","https://openalex.org/W3199667312","https://openalex.org/W4380993441"],"abstract_inverted_index":{"As":[0],"a":[1,47,57,140,154],"fundamental":[2],"task":[3],"across":[4],"computational":[5],"statistics,":[6],"scientific":[7],"computing":[8],"and":[9,65,90,104,111,119,160,177,195],"machine":[10],"learning,":[11],"sampling":[12,25],"from":[13],"high-dimensional":[14],"probability":[15,155],"distributions":[16],"has":[17],"received":[18],"increasing":[19],"attention":[20],"in":[21,153,214],"recent":[22],"years.":[23],"Numerous":[24],"algorithms":[26],"have":[27,44],"been":[28],"proposed,":[29],"among":[30],"which":[31],"underdamped":[32,40],"Langevin":[33,41],"Monte":[34],"Carlo":[35],"(ULMC)":[36],"methods":[37],"based":[38,101],"on":[39,102,165],"dynamics":[42],"(ULD)":[43],"emerged":[45],"as":[46,95,97],"class":[48],"of":[49,71,82,128,143,174,183],"efficient":[50],"ones.":[51,200],"In":[52,201],"this":[53],"work,":[54],"we":[55,163],"introduce":[56],"``universal\"":[58,76],"predictor-corrector":[59],"formulation":[60],"that":[61],"bridges":[62],"Euler-type,":[63],"UBU-type":[64,110,193],"randomized":[66,87,112,199],"schemes":[67,113,152],"through":[68],"different":[69],"choices":[70],"method":[72],"parameters.":[73],"Notably,":[74],"the":[75,126,166,202,206,219],"integrator":[77],"induces":[78],"two":[79,120],"novel":[80],"classes":[81],"low-cost":[83,86,91],"integrators,":[84],"termed":[85],"integrators":[88,93],"(LC-RIs)":[89],"UBU":[92],"(LC-UBUIs),":[94],"well":[96],"their":[98],"exponential-free":[99],"variants":[100],"polynomial":[103],"rational":[105],"approximations.":[106],"The":[107],"resulting":[108],"new":[109,178],"require":[114],"only":[115],"one":[116],"gradient":[117,129],"evaluation":[118],"Gaussians":[121,132],"per":[122,133],"iteration,":[123],"considerably":[124],"reducing":[125],"number":[127],"evaluations":[130],"or":[131],"iteration":[134],"required":[135],"by":[136],"existing":[137],"counterparts.":[138],"Further,":[139],"general":[141,150],"framework":[142,168],"long-time":[144],"error":[145,209],"analysis":[146],"is":[147],"developed":[148],"for":[149,186,192,198],"discretization":[151],"metric.":[156],"Under":[157],"certain":[158],"smoothness":[159],"non-log-concavity":[161],"conditions,":[162],"rely":[164],"unified":[167],"to":[169],"establish":[170],"non-asymptotic":[171,208],"$\\mathcal{W}_1$-error":[172],"bounds":[173,210],"both":[175],"old":[176],"schemes,":[179,188],"revealing":[180],"convergence":[181],"rates":[182],"order":[184,189,196],"$\\mathcal{O}(d^{\\frac{1}{2}}h)$":[185],"Euler-type":[187],"$\\mathcal{O}(d":[190],"h^2)$":[191],"ones":[194],"$\\mathcal{O}(d^{\\frac{1}{2}}h^{\\frac{3}{2}})$":[197],"strongly":[203],"convex":[204],"setting,":[205],"same":[207],"can":[211],"be":[212],"recovered":[213],"$\\mathcal{W}_2$-distance.":[215],"Numerical":[216],"experiments":[217],"corroborate":[218],"theoretical":[220],"findings.":[221]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-19T00:00:00"}