{"id":"https://openalex.org/W7118019378","doi":"https://doi.org/10.48550/arxiv.2512.23965","title":"Multimodal sampling via Schr\u00f6dinger-F\u00f6llmer samplers with temperatures","display_name":"Multimodal sampling via Schr\u00f6dinger-F\u00f6llmer samplers with temperatures","publication_year":2025,"publication_date":"2025-12-30","ids":{"openalex":"https://openalex.org/W7118019378","doi":"https://doi.org/10.48550/arxiv.2512.23965"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.23965","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.23965","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":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.2512.23965","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121824185","display_name":"Xiaojie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaojie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121801659","display_name":"Xiaoyan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaoyan","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":0.4009000062942505,"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":0.4009000062942505,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.0786999985575676,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.05959999933838844,"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/discretization","display_name":"Discretization","score":0.8429999947547913},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.64410001039505},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6065999865531921},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5454999804496765},{"id":"https://openalex.org/keywords/backward-euler-method","display_name":"Backward Euler method","score":0.5372999906539917},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.5121999979019165},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.4731999933719635},{"id":"https://openalex.org/keywords/eulers-formula","display_name":"Euler's formula","score":0.4553000032901764}],"concepts":[{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.8429999947547913},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.64410001039505},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6065999865531921},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5454999804496765},{"id":"https://openalex.org/C768646","wikidata":"https://www.wikidata.org/wiki/Q2736820","display_name":"Backward Euler method","level":3,"score":0.5372999906539917},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5267000198364258},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47769999504089355},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C62884695","wikidata":"https://www.wikidata.org/wiki/Q184871","display_name":"Euler's formula","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42829999327659607},{"id":"https://openalex.org/C105427703","wikidata":"https://www.wikidata.org/wiki/Q665193","display_name":"Discretization of continuous features","level":4,"score":0.42590001225471497},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3815999925136566},{"id":"https://openalex.org/C2986012078","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling interval","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.36890000104904175},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C75380026","wikidata":"https://www.wikidata.org/wiki/Q868454","display_name":"Euler method","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C2777767291","wikidata":"https://www.wikidata.org/wiki/Q1080291","display_name":"Sizing","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C48753275","wikidata":"https://www.wikidata.org/wiki/Q11216","display_name":"Numerical analysis","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.23965","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.23965","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":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.2512.23965","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.23965","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":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":{"Generating":[0],"samples":[1],"from":[2,112,198],"complex":[3],"and":[4,20,128,173,185],"high-dimensional":[5],"distributions":[6],"is":[7,122,136,164],"ubiquitous":[8],"in":[9,61,86,110,138,156,167,196],"various":[10],"scientific":[11,18],"fields":[12],"of":[13,43,58,94,119,133],"statistical":[14],"physics,":[15],"Bayesian":[16],"inference,":[17],"computing":[19],"machine":[21],"learning.":[22],"Very":[23],"recently,":[24],"Huang":[25],"et":[26],"al.":[27],"(IEEE":[28],"Trans.":[29],"Inform.":[30],"Theory,":[31],"2025)":[32],"proposed":[33,85],"new":[34],"Schr\u00f6dinger-F\u00f6llmer":[35,45,96],"samplers":[36,83],"(SFS),":[37],"based":[38,89],"on":[39,48,90,146],"the":[40,44,49,62,68,91,95,125,139,147,152,157,182,188],"Euler":[41,69,92],"discretization":[42,70,93,127],"diffusion":[46],"evolving":[47],"unit":[50,169],"interval":[51,170],"$[0,":[52,171],"1]$.":[53],"There,":[54],"a":[55,72,79,116,168],"convergence":[56,131,155,183],"rate":[57,132,184],"order":[59,134],"$\\mathcal{O}(\\sqrt{h})$":[60],"$L^2$-Wasserstein":[63,140],"distance":[64],"was":[65],"obtained":[66,137],"for":[67,124],"with":[71,98],"uniform":[73],"time":[74,126],"step-size":[75],"$h>0$.":[76],"By":[77],"introducing":[78],"temperature":[80],"parameter,":[81],"different":[82],"are":[84,107],"this":[87],"paper,":[88],"process":[97],"temperatures.":[99],"As":[100],"revealed":[101],"by":[102],"numerical":[103],"experiments,":[104],"high":[105],"temperatures":[106],"vital,":[108],"particularly":[109,195],"sampling":[111,197],"multimodal":[113,199],"distributions.":[114,200],"Further,":[115],"novel":[117],"approach":[118],"error":[120],"analysis":[121],"developed":[123],"an":[129],"enhanced":[130],"$\\mathcal{O}(h)$":[135],"distance,":[141],"under":[142],"certain":[143],"smoothness":[144],"conditions":[145],"drift.":[148],"This":[149],"significantly":[150],"improves":[151],"existing":[153],"order-half":[154],"aforementioned":[158],"paper.":[159],"Unlike":[160],"Langevin":[161,193],"samplers,":[162,194],"SFS":[163,189],"gradient-free,":[165],"works":[166],"1]$":[172],"does":[174],"not":[175],"require":[176],"any":[177],"ergodicity.":[178],"Numerical":[179],"experiments":[180],"confirm":[181],"show":[186],"that,":[187],"substantially":[190],"outperforms":[191],"vanilla":[192]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-01-02T00:00:00"}