{"id":"https://openalex.org/W7118020566","doi":"https://doi.org/10.48550/arxiv.2512.24381","title":"Tubular Riemannian Laplace Approximations for Bayesian Neural Networks","display_name":"Tubular Riemannian Laplace Approximations for Bayesian Neural Networks","publication_year":2025,"publication_date":"2025-12-30","ids":{"openalex":"https://openalex.org/W7118020566","doi":"https://doi.org/10.48550/arxiv.2512.24381"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.24381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.24381","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.2512.24381","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121759034","display_name":"Rodrigo Pereira David","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"David, Rodrigo Pereira","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5121759034"],"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.42809998989105225,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.42809998989105225,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.3142000138759613,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1014999970793724,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/laplaces-method","display_name":"Laplace's method","score":0.5842000246047974},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5368000268936157},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5202999711036682},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5},{"id":"https://openalex.org/keywords/laplace-transform","display_name":"Laplace transform","score":0.48170000314712524},{"id":"https://openalex.org/keywords/curvature","display_name":"Curvature","score":0.46380001306533813},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.45350000262260437},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.42250001430511475},{"id":"https://openalex.org/keywords/gaussian-curvature","display_name":"Gaussian curvature","score":0.39969998598098755}],"concepts":[{"id":"https://openalex.org/C22243797","wikidata":"https://www.wikidata.org/wiki/Q2058297","display_name":"Laplace's method","level":3,"score":0.5842000246047974},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5583999752998352},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5368000268936157},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.508899986743927},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5},{"id":"https://openalex.org/C97937538","wikidata":"https://www.wikidata.org/wiki/Q199691","display_name":"Laplace transform","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.46380001306533813},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.42250001430511475},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40049999952316284},{"id":"https://openalex.org/C16140857","wikidata":"https://www.wikidata.org/wiki/Q945953","display_name":"Gaussian curvature","level":3,"score":0.39969998598098755},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C193386753","wikidata":"https://www.wikidata.org/wiki/Q1130396","display_name":"Approximations of \u03c0","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3495999872684479},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3125},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2727000117301941},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C2779886137","wikidata":"https://www.wikidata.org/wiki/Q21030012","display_name":"Symmetry (geometry)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.24381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.24381","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.2512.24381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.24381","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":[{"score":0.447134405374527,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Laplace":[0,61],"approximations":[1,46],"are":[2],"among":[3],"the":[4,23,58,67,132,148,154],"simplest":[5],"and":[6,29,43,121,159],"most":[7],"practical":[8],"methods":[9],"for":[10],"approximate":[11],"Bayesian":[12],"inference":[13],"in":[14,111],"neural":[15],"networks,":[16],"yet":[17],"their":[18],"Euclidean":[19],"formulation":[20],"struggles":[21],"with":[22],"highly":[24],"anisotropic,":[25],"curved":[26],"loss":[27],"surfaces":[28],"large":[30],"symmetry":[31],"groups":[32],"that":[33,73,104,124],"characterize":[34],"modern":[35],"deep":[36],"models.":[37],"Recent":[38],"work":[39],"has":[40],"proposed":[41],"Riemannian":[42,60],"geometric":[44],"Gaussian":[45,102],"to":[47,49,86,109],"adapt":[48],"this":[50],"structure.":[51],"Building":[52],"on":[53,118],"these":[54],"ideas,":[55],"we":[56],"introduce":[57],"Tubular":[59],"(TRL)":[62],"approximation.":[63],"TRL":[64,97,125,151],"explicitly":[65],"models":[66],"posterior":[68],"as":[69,98],"a":[70,75,83,99,144],"probabilistic":[71],"tube":[72],"follows":[74],"low-loss":[76],"valley":[77],"induced":[78],"by":[79],"functional":[80],"symmetries,":[81],"using":[82],"Fisher/Gauss-Newton":[84],"metric":[85],"separate":[87],"prior-dominated":[88],"tangential":[89],"uncertainty":[90],"from":[91],"data-dominated":[92],"transverse":[93],"uncertainty.":[94],"We":[95],"interpret":[96],"scalable":[100],"reparametrised":[101],"approximation":[103],"utilizes":[105],"implicit":[106],"curvature":[107],"estimates":[108],"operate":[110],"high-dimensional":[112],"parameter":[113],"spaces.":[114],"Our":[115],"empirical":[116],"evaluation":[117],"ResNet-18":[119],"(CIFAR-10":[120],"CIFAR-100)":[122],"demonstrates":[123],"achieves":[126],"excellent":[127],"calibration,":[128],"matching":[129],"or":[130],"exceeding":[131],"reliability":[133],"of":[134,139,147],"Deep":[135],"Ensembles":[136],"(in":[137],"terms":[138],"ECE)":[140],"while":[141],"requiring":[142],"only":[143],"fraction":[145],"(1/5)":[146],"training":[149],"cost.":[150],"effectively":[152],"bridges":[153],"gap":[155],"between":[156],"single-model":[157],"efficiency":[158],"ensemble-grade":[160],"reliability.":[161]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-01-02T00:00:00"}