{"id":"https://openalex.org/W7156721016","doi":"https://doi.org/10.48550/arxiv.2604.24632","title":"Theoretical guarantees for stochastic gradient sampling methods via Gaussian convolution inequalities","display_name":"Theoretical guarantees for stochastic gradient sampling methods via Gaussian convolution inequalities","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7156721016","doi":"https://doi.org/10.48550/arxiv.2604.24632"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.24632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24632","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.2604.24632","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041259048","display_name":"Daniel Paulin","orcid":"https://orcid.org/0000-0001-7837-6452"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paulin, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134762319","display_name":"Peter A. Whalley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Whalley, Peter A.","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":0.9038000106811523,"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":0.9038000106811523,"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":0.039799999445676804,"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/T10229","display_name":"Geometric Analysis and Curvature Flows","score":0.010900000110268593,"subfield":{"id":"https://openalex.org/subfields/2604","display_name":"Applied 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/gaussian","display_name":"Gaussian","score":0.6075999736785889},{"id":"https://openalex.org/keywords/invariant-measure","display_name":"Invariant measure","score":0.5562000274658203},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.541700005531311},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5388000011444092},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.49239999055862427},{"id":"https://openalex.org/keywords/gaussian-measure","display_name":"Gaussian measure","score":0.46000000834465027},{"id":"https://openalex.org/keywords/probability-measure","display_name":"Probability measure","score":0.38690000772476196},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.3763999938964844},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.34209999442100525}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7117000222206116},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6075999736785889},{"id":"https://openalex.org/C115667082","wikidata":"https://www.wikidata.org/wiki/Q4200518","display_name":"Invariant measure","level":3,"score":0.5562000274658203},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.541700005531311},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5388000011444092},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5065000057220459},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C2777630202","wikidata":"https://www.wikidata.org/wiki/Q5527840","display_name":"Gaussian measure","level":3,"score":0.46000000834465027},{"id":"https://openalex.org/C21031990","wikidata":"https://www.wikidata.org/wiki/Q355020","display_name":"Probability measure","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3763999938964844},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C104824951","wikidata":"https://www.wikidata.org/wiki/Q830124","display_name":"Girsanov theorem","level":3,"score":0.32760000228881836},{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3075999915599823},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2777634741","wikidata":"https://www.wikidata.org/wiki/Q768993","display_name":"Wasserstein metric","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2720000147819519},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.2709999978542328},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C87698059","wikidata":"https://www.wikidata.org/wiki/Q1808960","display_name":"LTI system theory","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.24632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24632","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.2604.24632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24632","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":[{"display_name":"Reduced inequalities","score":0.49428245425224304,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,80],"derive":[1],"first-order":[2],"(in":[3],"the":[4,8,14,27,65,77,91,96,100],"stepsize)":[5],"bounds":[6,32],"on":[7,26,51,107],"bias":[9],"in":[10],"Wasserstein":[11],"distances":[12],"of":[13,17,46,87,102],"invariant":[15,52],"measure":[16,53],"stochastic":[18,28,103],"gradient":[19,29,104],"kinetic":[20],"Langevin":[21],"dynamics":[22],"with":[23,72,123],"minimal":[24],"assumptions":[25],"noise.":[30],"These":[31],"sharpen":[33],"existing":[34],"non-asymptotic":[35],"guarantees":[36],"for":[37],"stochastic-gradient":[38],"MCMC":[39,125],"methods":[40,106],"and":[41,76,116],"provide":[42],"a":[43,47,69,73,108,111,117],"quantitative":[44],"resolution":[45],"previously":[48],"open":[49],"problem":[50],"accuracy.":[54],"The":[55],"main":[56],"technical":[57],"ingredients":[58],"are":[59],"new":[60],"Gaussian":[61,70,78],"convolution":[62],"inequalities":[63,84],"controlling":[64],"Wasserstein-$p$":[66],"distance":[67],"between":[68],"convolved":[71],"mean-zero":[74],"perturbation":[75],"itself.":[79],"anticipate":[81],"that":[82],"these":[83],"will":[85],"be":[86],"independent":[88],"interest":[89],"beyond":[90],"present":[92],"application.":[93],"To":[94],"complement":[95],"theory,":[97],"we":[98],"illustrate":[99],"benefits":[101],"sampling":[105],"one-dimensional":[109],"model,":[110],"Bayesian":[112,118],"logistic":[113],"regression":[114],"example":[115],"random-effect":[119],"model":[120],"including":[121],"comparison":[122],"pseudo-marginal":[124],"methods.":[126]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-29T00:00:00"}