{"id":"https://openalex.org/W7160862205","doi":"https://doi.org/10.48550/arxiv.2605.07939","title":"Accelerating Langevin Monte Carlo via Efficient Stochastic Runge--Kutta Methods beyond Log-Concavity","display_name":"Accelerating Langevin Monte Carlo via Efficient Stochastic Runge--Kutta Methods beyond Log-Concavity","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160862205","doi":"https://doi.org/10.48550/arxiv.2605.07939"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07939","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07939","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"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.2605.07939","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135903931","display_name":"Bin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135889740","display_name":"Xiaojie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaojie","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":0.9326000213623047,"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":0.9326000213623047,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.022099999710917473,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.6563000082969666},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.5582000017166138},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5440999865531921},{"id":"https://openalex.org/keywords/langevin-dynamics","display_name":"Langevin dynamics","score":0.5238999724388123},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4952999949455261},{"id":"https://openalex.org/keywords/rejection-sampling","display_name":"Rejection sampling","score":0.49320000410079956},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.49149999022483826},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4068000018596649}],"concepts":[{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.6563000082969666},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.5582000017166138},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5440999865531921},{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.515500009059906},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C187192777","wikidata":"https://www.wikidata.org/wiki/Q381699","display_name":"Rejection sampling","level":5,"score":0.49320000410079956},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.49149999022483826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48899999260902405},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4081999957561493},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C13153151","wikidata":"https://www.wikidata.org/wiki/Q1639846","display_name":"Hybrid Monte Carlo","level":4,"score":0.397599995136261},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38089999556541443},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.3564000129699707},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C170593435","wikidata":"https://www.wikidata.org/wiki/Q4128565","display_name":"Slice sampling","level":4,"score":0.3346000015735626},{"id":"https://openalex.org/C132725507","wikidata":"https://www.wikidata.org/wiki/Q39879","display_name":"Monte Carlo integration","level":5,"score":0.31929999589920044},{"id":"https://openalex.org/C204493344","wikidata":"https://www.wikidata.org/wiki/Q6904698","display_name":"Monte Carlo method in statistical physics","level":5,"score":0.3179999887943268},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3163999915122986},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C15482360","wikidata":"https://www.wikidata.org/wiki/Q15238499","display_name":"Monte Carlo algorithm","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C63320529","wikidata":"https://www.wikidata.org/wiki/Q7269435","display_name":"Quasi-Monte Carlo method","level":5,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07939","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07939","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.07939","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07939","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"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":{"Sampling":[0],"from":[1],"a":[2,7,45,119,131],"high-dimensional":[3,40],"probability":[4],"distribution":[5],"is":[6,90,128],"fundamental":[8],"algorithmic":[9],"task":[10],"arising":[11],"in":[12,39,115,130,139],"wide-ranging":[13],"applications":[14],"across":[15],"multiple":[16],"disciplines,":[17],"including":[18],"scientific":[19],"computing,":[20],"computational":[21],"statistics":[22],"and":[23,48,93],"machine":[24],"learning.":[25],"Langevin":[26,67],"Monte":[27],"Carlo":[28],"(LMC)":[29],"algorithms":[30,112],"are":[31,113,150],"among":[32],"the":[33,65,72,86,110,135,140,145,155,158],"most":[34],"widely":[35],"used":[36],"sampling":[37,51,160],"methods":[38],"settings.":[41],"This":[42],"paper":[43],"introduces":[44],"novel":[46],"higher-order":[47],"Hessian-free":[49],"LMC":[50,76],"algorithm":[52,89],"based":[53],"on":[54],"an":[55],"efficient":[56],"stochastic":[57],"Runge--Kutta":[58,74],"method":[59],"of":[60,109,123,157],"strong":[61],"order":[62,124],"$1.5$":[63],"for":[64,99],"overdamped":[66],"dynamics.":[68],"In":[69,117],"contrast":[70],"to":[71,153],"existing":[73],"type":[75],"(Li":[77],"et":[78],"al.,":[79],"2019)":[80],"involved":[81],"with":[82],"three":[83],"gradient":[84,97],"evaluations,":[85],"newly":[87],"proposed":[88,111],"computationally":[91],"cheaper":[92],"requires":[94],"only":[95],"two":[96],"evaluations":[98],"one":[100],"iteration.":[101],"Under":[102],"certain":[103],"log-smooth":[104],"conditions,":[105],"non-asymptotic":[106],"error":[107],"bounds":[108],"analyzed":[114],"$\\mathcal{W}_2$-distance.":[116],"particular,":[118],"uniform-in-time":[120],"convergence":[121,136],"rate":[122,137],"$O(d":[125],"^{\\frac32}":[126],"h^{\\frac32})$":[127],"derived":[129],"non-log-concave":[132],"setting,":[133],"matching":[134],"proved":[138],"aforementioned":[141],"work":[142],"but":[143],"under":[144],"log-concavity":[146],"condition.":[147],"Numerical":[148],"experiments":[149],"finally":[151],"presented":[152],"demonstrate":[154],"effectiveness":[156],"new":[159],"algorithm.":[161]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-12T00:00:00"}