{"id":"https://openalex.org/W7222009396","doi":"https://doi.org/10.48550/arxiv.2610.19670","title":"SULA: Robust Langevin Sampling via Drift-Diffusion Saturation","display_name":"SULA: Robust Langevin Sampling via Drift-Diffusion Saturation","publication_year":2026,"publication_date":"2026-10-14","ids":{"openalex":"https://openalex.org/W7222009396","doi":"https://doi.org/10.48550/arxiv.2610.19670"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.19670","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.19670","pdf_url":"https://arxiv.org/pdf/2610.19670","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/2610.19670","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031692665","display_name":"Ritik Soni","orcid":"https://orcid.org/0009-0008-5305-7509","observed_orcids":["https://orcid.org/0009-0008-5305-7509"]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soni, Ritik","raw_affiliation_strings":["Department of Statistics and Data Science Indian Institute of Technology Kanpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075706077","display_name":"Dootika Vats","orcid":"https://orcid.org/0000-0001-9453-0368","observed_orcids":["https://orcid.org/0000-0001-9453-0368"]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vats, Dootika","raw_affiliation_strings":["Department of Statistics and Data Science Indian Institute of Technology Kanpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94234084"],"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":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/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/unadjusted-langevin-algorithm","display_name":"unadjusted Langevin algorithm","score":0.9020000100135803},{"id":"https://openalex.org/keywords/stochastic-gradient-langevin-dynamics","display_name":"stochastic gradient Langevin dynamics","score":0.8970000147819519},{"id":"https://openalex.org/keywords/non-lipschitz-drift","display_name":"non-Lipschitz drift","score":0.972000002861023},{"id":"https://openalex.org/keywords/weak-convergence","display_name":"weak convergence","score":0.9229999780654907},{"id":"https://openalex.org/keywords/geometric-ergodicity","display_name":"geometric ergodicity","score":0.996999979019165},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5260000228881836},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.75}],"concepts":[{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.6158999800682068},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.6093000173568726},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5192000269889832},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5105000138282776},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.41359999775886536},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C2777577648","wikidata":"https://www.wikidata.org/wiki/Q584537","display_name":"Langevin equation","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3370000123977661},{"id":"https://openalex.org/C115667082","wikidata":"https://www.wikidata.org/wiki/Q4200518","display_name":"Invariant measure","level":3,"score":0.3312999904155731},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C75438885","wikidata":"https://www.wikidata.org/wiki/Q3403615","display_name":"Large deviations theory","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C112401455","wikidata":"https://www.wikidata.org/wiki/Q178036","display_name":"Brownian motion","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.27489998936653137},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2779664328","wikidata":"https://www.wikidata.org/wiki/Q6311158","display_name":"Jump diffusion","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C98951983","wikidata":"https://www.wikidata.org/wiki/Q7604341","display_name":"Stationary distribution","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C2777634741","wikidata":"https://www.wikidata.org/wiki/Q768993","display_name":"Wasserstein metric","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C130603088","wikidata":"https://www.wikidata.org/wiki/Q4976526","display_name":"Brownian dynamics","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25540000200271606},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.19670","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.19670","pdf_url":"https://arxiv.org/pdf/2610.19670","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.19670","doi":"https://doi.org/10.48550/arxiv.2610.19670","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.19670","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.19670","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.19670","pdf_url":"https://arxiv.org/pdf/2610.19670","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306227","display_name":"Arthritis National Research Foundation","ror":"https://ror.org/03abbex33"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222009396.pdf","grobid_xml":"https://content.openalex.org/works/W7222009396.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415146224","https://openalex.org/W4411194572","https://openalex.org/W4389364452","https://openalex.org/W2766600609","https://openalex.org/W2950555252","https://openalex.org/W2949188030","https://openalex.org/W7201886815","https://openalex.org/W2923695424","https://openalex.org/W4407231855","https://openalex.org/W2788191306"],"abstract_inverted_index":{"The":[0,80],"unadjusted":[1,57],"Langevin":[2,58,78,129],"algorithm":[3,59],"(ULA)":[4],"and":[5,82,108,111,142,191],"its":[6,147],"stochastic-gradient":[7,161],"variant,":[8],"SGLD,":[9],"are":[10,85],"workhorses":[11],"of":[12,96,106,146,163,177],"modern":[13],"Bayesian":[14],"machine":[15],"learning,":[16],"but":[17],"can":[18,39],"be":[19],"fragile":[20],"when":[21],"faced":[22],"with":[23,67,76,121],"a":[24,28,63,68,122,160,171],"target":[25,153],"distribution":[26],"possessing":[27],"non-Lipschitz":[29],"drift.":[30],"In":[31],"such":[32],"settings,":[33],"the":[34,47,55,77,90,97,104,128,132,136,144,152,167,178],"expected":[35],"squared":[36,92],"jump":[37],"distance":[38],"grow":[40],"rapidly,":[41],"leading":[42],"to":[43,87,103,127,151,189],"numerical":[44],"instability":[45],"or":[46],"need":[48],"for":[49],"prohibitively":[50],"small":[51],"step-sizes.":[52],"We":[53,114],"propose":[54],"saturated":[56,64],"(SULA)":[60],"that":[61,89,143,165],"pairs":[62],"gradient":[65,169,179],"drift":[66,81],"gradient-informed":[69],"state-dependent":[70],"diffusion,":[71],"while":[72],"preserving":[73],"first-order":[74],"consistency":[75],"diffusion.":[79],"diffusion":[83,130],"terms":[84],"chosen":[86],"guarantee":[88],"one-step":[91],"update":[93],"is":[94,101,139,154],"independent":[95],"gradient.":[98],"Consequently,":[99],"SULA":[100,120,137,164],"robust":[102],"choice":[105],"step-size":[107,123],"preserves":[109],"estimation":[110],"prediction":[112],"quality.":[113],"provide":[115],"sufficient":[116],"conditions":[117],"under":[118,175],"which":[119],"$h$":[124],"converges":[125],"weakly":[126],"at":[131],"standard":[133],"$O(h)$":[134],"rate,":[135],"chain":[138],"geometrically":[140],"ergodic,":[141],"bias":[145],"invariant":[148],"measure":[149],"relative":[150],"$O(h)$.":[155],"Further,":[156],"we":[157],"develop":[158],"SG-SULA,":[159],"version":[162],"rescales":[166],"stochastic":[168],"using":[170],"Gaussian":[172],"CDF":[173],"correction":[174],"Gaussianity":[176],"noise.":[180],"Numerical":[181],"experiments":[182],"on":[183],"various":[184],"examples":[185],"demonstrate":[186],"SULA's":[187],"robustness":[188],"tuning":[190],"SG-SULA's":[192],"improved":[193],"predictive":[194],"performance.":[195]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-16T00:00:00"}