{"id":"https://openalex.org/W7160612532","doi":"https://doi.org/10.48550/arxiv.2605.06091","title":"Time-Inhomogeneous Preconditioned Langevin Dynamics","display_name":"Time-Inhomogeneous Preconditioned Langevin Dynamics","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160612532","doi":"https://doi.org/10.48550/arxiv.2605.06091"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.06091","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06091","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.2605.06091","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135728386","display_name":"Alexander Falk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Falk, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115911181","display_name":"Laurenz Nagler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nagler, Laurenz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030032319","display_name":"Andreas Habring","orcid":"https://orcid.org/0000-0002-1201-5782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Habring, Andreas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032205387","display_name":"Thomas Pock","orcid":"https://orcid.org/0000-0001-6120-1058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pock, Thomas","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.29319998621940613,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.29319998621940613,"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"}},{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.2842999994754791,"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/T12303","display_name":"Tensor decomposition and applications","score":0.21389999985694885,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5439000129699707},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.5264000296592712},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.492900013923645},{"id":"https://openalex.org/keywords/curvature","display_name":"Curvature","score":0.42260000109672546},{"id":"https://openalex.org/keywords/langevin-dynamics","display_name":"Langevin dynamics","score":0.4034999907016754},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.38040000200271606},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.3589000105857849},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.35519999265670776},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.3456999957561493}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5439000129699707},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.47909998893737793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4429999887943268},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41749998927116394},{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34220001101493835},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C2777032711","wikidata":"https://www.wikidata.org/wiki/Q5318993","display_name":"Dynamic mode decomposition","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C88271906","wikidata":"https://www.wikidata.org/wiki/Q786973","display_name":"Autocovariance","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.06091","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06091","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.2605.06091","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06091","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Langevin":[0,58],"sampling":[1],"from":[2],"distributions":[3,29],"of":[4,72,127,153,206],"the":[5,34,38,65,69,103,128,132,150,154,204,207],"form":[6],"$p(x)":[7],"\\propto":[8],"\\exp(-\u03a8(x))$":[9],"faces":[10],"two":[11],"major":[12],"challenges:":[13],"(global)":[14],"mode":[15,19,46,84,88],"coverage":[16,85],"and":[17,43,86,90,109,139,161,165,193],"(local)":[18],"exploration.":[20],"The":[21],"first":[22],"challenge":[23],"is":[24,55],"particularly":[25],"relevant":[26],"for":[27,140],"multi-modal":[28],"with":[30,60,183],"disjoint":[31],"modes,":[32],"whereas":[33],"second":[35],"arises":[36],"when":[37],"potential":[39],"$\u03a8$":[40],"exhibits":[41],"diverse":[42],"ill-conditioned":[44],"local":[45,70,87],"geometry.":[47],"To":[48,97],"address":[49],"these":[50],"challenges,":[51],"a":[52,80,107,121,141,188,195],"common":[53],"approach":[54],"to":[56],"precondition":[57],"dynamics":[59,130],"problem-specific":[61],"information,":[62],"such":[63],"as":[64],"sample":[66],"covariance":[67],"or":[68],"curvature":[71],"$\u03a8$.":[73],"However,":[74],"existing":[75,151],"preconditioner":[76],"choices":[77],"inherently":[78],"involve":[79],"trade-off":[81],"between":[82],"global":[83],"exploration,":[89],"no":[91],"prior":[92,176],"method":[93],"resolves":[94],"both":[95,116,135],"simultaneously.":[96],"overcome":[98],"this":[99],"limitation,":[100],"we":[101,179],"propose":[102],"TIPreL,":[104],"which":[105,170],"introduces":[106],"time-":[108,160],"position-dependent":[110],"preconditioner.":[111],"This":[112],"design":[113],"effectively":[114],"addresses":[115],"challenges":[117],"mentioned":[118],"above":[119],"within":[120],"single":[122],"framework.":[123],"We":[124],"establish":[125],"convergence":[126,158],"resulting":[129],"in":[131,136,200],"Wasserstein-2":[133],"distance":[134],"continuous":[137],"time":[138],"tamed":[142],"Euler":[143],"discretization.":[144],"In":[145],"particular,":[146],"our":[147],"analysis":[148],"extends":[149],"state":[152],"art":[155],"by":[156,175],"proving":[157],"under":[159],"space-dependent":[162],"diffusion":[163],"coefficients,":[164],"only":[166],"locally":[167],"Lipschitz":[168],"drifts,":[169],"has":[171],"not":[172],"been":[173],"covered":[174],"work.":[177],"Finally,":[178],"experimentally":[180],"compare":[181],"TIPreL":[182],"competing":[184],"preconditioning":[185],"schemes":[186],"on":[187,194],"two-dimensional,":[189],"severely":[190],"ill-posed":[191],"example":[192],"Bayesian":[196],"logistic":[197],"regression":[198],"task":[199],"higher":[201],"dimensions,":[202],"confirming":[203],"efficiency":[205],"proposed":[208],"method.":[209]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-09T00:00:00"}