{"id":"https://openalex.org/W7130530199","doi":"https://doi.org/10.48550/arxiv.2602.15925","title":"Robust Stochastic Gradient Posterior Sampling with Lattice Based Discretisation","display_name":"Robust Stochastic Gradient Posterior Sampling with Lattice Based Discretisation","publication_year":2026,"publication_date":"2026-02-17","ids":{"openalex":"https://openalex.org/W7130530199","doi":"https://doi.org/10.48550/arxiv.2602.15925"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.15925","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126406007","display_name":"Zier Mensch","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mensch, Zier","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057175978","display_name":"Lars Holdijk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Holdijk, Lars","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061125105","display_name":"Samuel Duffield","orcid":"https://orcid.org/0000-0002-8656-8734"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duffield, Samuel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126429611","display_name":"Maxwell Aifer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aifer, Maxwell","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088973719","display_name":"Patrick J. Coles","orcid":"https://orcid.org/0000-0001-9879-8425"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Coles, Patrick J.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120993396","display_name":"Max Welling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Welling, Max","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126437747","display_name":"Miranda C. N. Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Miranda C. N.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5126406007"],"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":0.9684000015258789,"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":0.9684000015258789,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01269999984651804,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.00419999985024333,"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":0.6348999738693237},{"id":"https://openalex.org/keywords/random-walk","display_name":"Random walk","score":0.5759000182151794},{"id":"https://openalex.org/keywords/langevin-dynamics","display_name":"Langevin dynamics","score":0.5447999835014343},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5133000016212463},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4991999864578247},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4964999854564667},{"id":"https://openalex.org/keywords/lattice","display_name":"Lattice (music)","score":0.47769999504089355},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.396699994802475}],"concepts":[{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6348999738693237},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6255000233650208},{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.5759000182151794},{"id":"https://openalex.org/C2780004032","wikidata":"https://www.wikidata.org/wiki/Q6485978","display_name":"Langevin dynamics","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5133000016212463},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4991999864578247},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4964999854564667},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.47769999504089355},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.39250001311302185},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3562000095844269},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3450999855995178},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3434999883174896},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3181999921798706},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27480000257492065},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.15925","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.15925","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15925","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.15925","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"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":{"Stochastic-gradient":[0],"MCMC":[1],"methods":[2],"enable":[3],"scalable":[4],"Bayesian":[5,85],"posterior":[6],"sampling":[7],"but":[8],"often":[9],"suffer":[10],"from":[11],"sensitivity":[12],"to":[13,62],"minibatch":[14,63],"size":[15,64],"and":[16,87,107],"gradient":[17,80,105],"noise.":[18],"To":[19],"address":[20],"this,":[21],"we":[22,72],"propose":[23],"Stochastic":[24,40],"Gradient":[25,41],"Lattice":[26,34],"Random":[27,35],"Walk":[28,36],"(SGLRW),":[29],"an":[30],"extension":[31],"of":[32,54,77,103],"the":[33,51,55,101],"discretization.":[37],"Unlike":[38],"conventional":[39],"Langevin":[42],"Dynamics":[43],"(SGLD),":[44],"SGLRW":[45,91],"introduces":[46],"stochastic":[47],"noise":[48],"only":[49],"through":[50],"off-diagonal":[52],"elements":[53],"update":[56],"covariance;":[57],"this":[58],"yields":[59],"greater":[60],"robustness":[61],"while":[65],"retaining":[66],"asymptotic":[67],"correctness.":[68],"Furthermore,":[69],"as":[70],"comparison":[71],"analyze":[73],"a":[74],"natural":[75],"analogue":[76],"SGLD":[78,97],"utilizing":[79],"clipping.":[81],"Experimental":[82],"validation":[83],"on":[84],"regression":[86],"classification":[88],"demonstrates":[89],"that":[90],"remains":[92],"stable":[93],"in":[94,100],"regimes":[95],"where":[96],"fails,":[98],"including":[99],"presence":[102],"heavy-tailed":[104],"noise,":[106],"matches":[108],"or":[109],"improves":[110],"predictive":[111],"performance.":[112]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-20T00:00:00"}