{"id":"https://openalex.org/W7160633375","doi":"https://doi.org/10.48550/arxiv.2605.06392","title":"ADELIA: Automatic Differentiation for Efficient Laplace Inference Approximations","display_name":"ADELIA: Automatic Differentiation for Efficient Laplace Inference Approximations","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160633375","doi":"https://doi.org/10.48550/arxiv.2605.06392"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.06392","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06392","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.2605.06392","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120447623","display_name":"Afif Boudaoud","orcid":"https://orcid.org/0009-0003-8662-6353"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boudaoud, Afif","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072469042","display_name":"Lisa Gaedke-Merzh\u00e4user","orcid":"https://orcid.org/0000-0002-7586-2727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaedke-Merzh\u00e4user, Lisa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070514518","display_name":"Alexandros Nikolaos Ziogas","orcid":"https://orcid.org/0000-0002-4328-9751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziogas, Alexandros Nikolaos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093876743","display_name":"Vincent Maillou","orcid":"https://orcid.org/0000-0003-4861-3298"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maillou, Vincent","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044806450","display_name":"Alexandru Calotoiu","orcid":"https://orcid.org/0000-0001-9095-9108"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Calotoiu, Alexandru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077355144","display_name":"Marcin Copik","orcid":"https://orcid.org/0000-0002-7606-5519"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Copik, Marcin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135719628","display_name":"H\u00e5vard Rue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rue, H\u00e5vard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058537769","display_name":"Mathieu Luisier","orcid":"https://orcid.org/0000-0002-2212-7972"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luisier, Mathieu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135712458","display_name":"Torsten Hoefler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoefler, Torsten","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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.8964999914169312,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.8964999914169312,"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":0.011500000022351742,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.009499999694526196,"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/inference","display_name":"Inference","score":0.6969000101089478},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5932999849319458},{"id":"https://openalex.org/keywords/laplace-transform","display_name":"Laplace transform","score":0.5573999881744385},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5526000261306763},{"id":"https://openalex.org/keywords/automatic-differentiation","display_name":"Automatic differentiation","score":0.4788999855518341},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.46219998598098755},{"id":"https://openalex.org/keywords/laplaces-method","display_name":"Laplace's method","score":0.45899999141693115},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.45719999074935913}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6969000101089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5990999937057495},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5932999849319458},{"id":"https://openalex.org/C97937538","wikidata":"https://www.wikidata.org/wiki/Q199691","display_name":"Laplace transform","level":2,"score":0.5573999881744385},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5526000261306763},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5055000185966492},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.48170000314712524},{"id":"https://openalex.org/C133512626","wikidata":"https://www.wikidata.org/wiki/Q787371","display_name":"Automatic differentiation","level":3,"score":0.4788999855518341},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.46219998598098755},{"id":"https://openalex.org/C22243797","wikidata":"https://www.wikidata.org/wiki/Q2058297","display_name":"Laplace's method","level":3,"score":0.45899999141693115},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4503999948501587},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4447999894618988},{"id":"https://openalex.org/C126909462","wikidata":"https://www.wikidata.org/wiki/Q5369501","display_name":"Embarrassingly parallel","level":3,"score":0.4357999861240387},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.40540000796318054},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33629998564720154},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.06392","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06392","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.2605.06392","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06392","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spatio-temporal":[0],"Bayesian":[1],"inference":[2,18],"drives":[3],"environmental":[4],"and":[5,54,119],"health":[6],"sciences":[7],"using":[8],"latent":[9,129],"Gaussian":[10],"models.":[11],"Integrated":[12],"Nested":[13],"Laplace":[14],"Approximations":[15],"(INLA)":[16],"enable":[17],"for":[19],"these":[20],"models":[21,124],"at":[22],"HPC":[23],"scale":[24],"but":[25,51,74],"rely":[26],"on":[27,106,122],"derivative-based":[28],"optimization":[29],"over":[30],"$d$":[31],"hyperparameters.":[32],"State-of-the-art":[33],"INLA":[34,92],"implementations":[35],"approximate":[36],"derivatives":[37],"via":[38],"central":[39],"finite":[40],"differences":[41],"(FD),":[42],"requiring":[43],"$2d{+}1$":[44],"evaluations.":[45],"These":[46],"evaluations":[47],"are":[48],"embarrassingly":[49],"parallel,":[50],"total":[52],"work":[53],"energy":[55],"grow":[56],"with":[57,94,125],"$d$,":[58,73],"limiting":[59],"time-to-solution":[60],"under":[61],"fixed":[62],"budgets.":[63],"Reverse-mode":[64],"automatic":[65],"differentiation":[66],"(AD)":[67],"computes":[68],"exact":[69],"gradients":[70],"independently":[71],"of":[72],"its":[75],"efficient":[76],"application":[77],"to":[78,127,137,140],"INLA's":[79],"structured-sparse":[80],"kernels":[81],"is":[82],"an":[83],"open":[84],"challenge.":[85],"We":[86,103,114],"present":[87],"ADELIA,":[88],"the":[89],"first":[90],"AD-enabled":[91],"implementation":[93],"a":[95],"structure-exploiting":[96],"multi-GPU":[97],"backward":[98],"pass":[99],"leveraging":[100],"model":[101],"sparsity.":[102],"evaluate":[104],"ADELIA":[105],"ten":[107],"benchmark":[108],"models,":[109],"including":[110],"real-world":[111],"air-pollution":[112],"monitoring.":[113],"achieve":[115],"$4.2$--$7.9\\times$":[116],"per-gradient":[117],"speedups":[118],"reliable":[120],"convergence":[121],"production-scale":[123],"up":[126],"1.9M":[128],"variables,":[130],"where":[131],"FD":[132,145],"struggles.":[133],"Even":[134],"when":[135],"scaled":[136],"16--32":[138],"GPUs":[139],"match":[141],"ADELIA's":[142],"wall-clock":[143],"time,":[144],"consumes":[146],"$5$--$8\\times$":[147],"more":[148],"energy.":[149]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-09T00:00:00"}