{"id":"https://openalex.org/W7052638632","doi":null,"title":"Scalable approximate inference methods for Bayesian deep learning","display_name":"Scalable approximate inference methods for Bayesian deep learning","publication_year":2023,"publication_date":"2023-05-28","ids":{"openalex":"https://openalex.org/W7052638632"},"language":"en","primary_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10169549","doi":null,"is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10169549/","pdf_url":"https://discovery.ucl.ac.uk/id/eprint/10169549/2/thesis.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Doctoral thesis, UCL (University College London).","raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://discovery.ucl.ac.uk/id/eprint/10169549/2/thesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ritter, Julian Hippolyt","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ritter, Julian Hippolyt","raw_affiliation_strings":["Department of Computer Science University College London","Philosophy of University College London "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University College London","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"Philosophy of University College London ","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45129253"],"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":true,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.986299991607666,"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":0.986299991607666,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.005100000184029341,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0012000000569969416,"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/bayesian-deep-learning","display_name":"Bayesian deep learning","score":0.8610000014305115},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"approximate inference","score":0.9750000238418579},{"id":"https://openalex.org/keywords/laplace-approximation","display_name":"Laplace approximation","score":0.8629999756813049},{"id":"https://openalex.org/keywords/parameter-correlation","display_name":"parameter correlation","score":0.7310000061988831},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.8889999985694885},{"id":"https://openalex.org/keywords/uncertainty-estimation","display_name":"uncertainty estimation","score":0.8029999732971191},{"id":"https://openalex.org/keywords/continual-learning","display_name":"continual learning","score":0.9980000257492065},{"id":"https://openalex.org/keywords/variational-bayesian-inference","display_name":"variational inference","score":0.9860000014305115},{"id":"https://openalex.org/keywords/sparse-gaussian-processes","display_name":"sparse Gaussian processes","score":0.8989999890327454},{"id":"https://openalex.org/keywords/matrix-normal-distribution","display_name":"matrix normal distribution","score":0.7639999985694885},{"id":"https://openalex.org/keywords/hierarchical-models","display_name":"hierarchical models","score":0.6060000061988831},{"id":"https://openalex.org/keywords/probabilistic-programming","display_name":"probabilistic programming","score":0.8130000233650208},{"id":"https://openalex.org/keywords/pyro","display_name":"Pyro","score":0.8600000143051147},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.8100000023841858},{"id":"https://openalex.org/keywords/neural-radiance-fields","display_name":"neural radiance fields","score":0.9769999980926514}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5946000218391418},{"id":"https://openalex.org/C22243797","wikidata":"https://www.wikidata.org/wiki/Q2058297","display_name":"Laplace's method","level":3,"score":0.5640000104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5414999723434448},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44850000739097595},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4343000054359436},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.4296000003814697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42570000886917114},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.39809998869895935},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35249999165534973},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C97937538","wikidata":"https://www.wikidata.org/wiki/Q199691","display_name":"Laplace transform","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C113313756","wikidata":"https://www.wikidata.org/wiki/Q332791","display_name":"Diagonal matrix","level":3,"score":0.325300008058548},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3084000051021576},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C39482219","wikidata":"https://www.wikidata.org/wiki/Q192826","display_name":"Kronecker delta","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C177384507","wikidata":"https://www.wikidata.org/wiki/Q1149000","display_name":"Multivariate normal distribution","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10169549","doi":null,"is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10169549/","pdf_url":"https://discovery.ucl.ac.uk/id/eprint/10169549/2/thesis.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Doctoral thesis, UCL (University College London).","raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10169549","doi":null,"is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10169549/","pdf_url":"https://discovery.ucl.ac.uk/id/eprint/10169549/2/thesis.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Doctoral thesis, UCL (University College London).","raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7052638632.pdf","grobid_xml":"https://content.openalex.org/works/W7052638632.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1673923490","https://openalex.org/W1729198099","https://openalex.org/W1779452081","https://openalex.org/W1945616565","https://openalex.org/W2113839990","https://openalex.org/W2167839676","https://openalex.org/W2186615578","https://openalex.org/W2242818861","https://openalex.org/W2266471546","https://openalex.org/W2319920447","https://openalex.org/W2342840547","https://openalex.org/W2519091744","https://openalex.org/W2583761661","https://openalex.org/W2586067474","https://openalex.org/W2626325961","https://openalex.org/W2750384547","https://openalex.org/W2752366553","https://openalex.org/W2767630563","https://openalex.org/W2768267830","https://openalex.org/W2770864858","https://openalex.org/W2784590060","https://openalex.org/W2785783085","https://openalex.org/W2786767221","https://openalex.org/W2804746922","https://openalex.org/W2810382146","https://openalex.org/W2890467057","https://openalex.org/W2890984855","https://openalex.org/W2894356164","https://openalex.org/W2896457183","https://openalex.org/W2899063268","https://openalex.org/W2902363477","https://openalex.org/W2903479731","https://openalex.org/W2905631704","https://openalex.org/W2943035085","https://openalex.org/W2947654433","https://openalex.org/W2955023002","https://openalex.org/W2964121744","https://openalex.org/W2964137095","https://openalex.org/W2973727699","https://openalex.org/W2991954512","https://openalex.org/W2993180713","https://openalex.org/W3003921671","https://openalex.org/W3009733954","https://openalex.org/W3030163527","https://openalex.org/W3037787951","https://openalex.org/W3042719542","https://openalex.org/W3080555959","https://openalex.org/W3092641135","https://openalex.org/W3094105627","https://openalex.org/W3095936509","https://openalex.org/W3099497569","https://openalex.org/W3101316131","https://openalex.org/W3108753481","https://openalex.org/W3134221632","https://openalex.org/W3154315030","https://openalex.org/W3170763958","https://openalex.org/W3170909290","https://openalex.org/W3212621823","https://openalex.org/W4221147084","https://openalex.org/W4319988532","https://openalex.org/W4387449201","https://openalex.org/W7045062981","https://openalex.org/W7094282185"],"related_works":["https://openalex.org/W3132398892","https://openalex.org/W6925395680","https://openalex.org/W4416965047","https://openalex.org/W6958793641","https://openalex.org/W2888872523","https://openalex.org/W7204085090","https://openalex.org/W6962834467","https://openalex.org/W3044497662","https://openalex.org/W2966381196","https://openalex.org/W2977512348"],"abstract_inverted_index":{"This":[0,36,257],"thesis":[1],"proposes":[2],"multiple":[3],"methods":[4,51],"for":[5,39,127],"approximate":[6],"inference":[7,129],"in":[8,58,103,109,111,130,172,260],"deep":[9],"Bayesian":[10,238],"neural":[11,131,150,235,277,283],"networks":[12,236,278],"split":[13],"across":[14],"three":[15],"parts.":[16],"\\nThe":[17,120,217],"first":[18],"part":[19,122,219],"develops":[20],"a":[21,27,84,169,173,201,214,222,248,261],"scalable":[22],"Laplace":[23,67],"approximation":[24,32,37,102],"based":[25,134,179],"on":[26,135,180,227],"block-":[28],"diagonal":[29,50,101],"Kronecker":[30],"factored":[31],"of":[33,49,62,64,183,200,208,211,213,229,263],"the":[34,44,55,59,65,73,87,93,100,112,115,140,198,209],"Hessian.":[35],"accounts":[38],"parameter":[40],"correlations":[41,91],"\u2013":[42,52],"overcoming":[43],"overly":[45],"restrictive":[46],"independence":[47],"assumption":[48],"while":[53,204],"avoiding":[54],"quadratic":[56],"scaling":[57],"num-":[60],"ber":[61],"parameters":[63,94,212],"full":[66],"approximation.":[68],"The":[69,154,177],"chapter":[70],"further":[71],"extends":[72],"method":[74,171],"to":[75,96,149,186,195,231,242,253,279],"online":[76],"learning":[77],"where":[78],"datasets":[79],"are":[80],"observed":[81],"one":[82,133,142],"at":[83],"time.":[85],"As":[86],"experiments":[88],"demonstrate,":[89],"modelling":[90],"between":[92],"leads":[95],"improved":[97],"performance":[98,194],"over":[99,139,271],"uncertainty":[104,192,281],"estimation":[105,193],"and":[106],"continual":[107],"learning,":[108],"particular":[110],"latter":[113],"setting":[114],"improvements":[116],"can":[117,165],"be":[118,166],"substantial.":[119],"second":[121],"explores":[123],"two":[124],"parameter-efficient":[125],"approaches":[126],"variational":[128],"networks,":[132],"factorised":[136],"binary":[137],"distributions":[138],"weights,":[141],"extending":[143],"ideas":[144],"from":[145,265],"sparse":[146],"Gaussian":[147,162],"processes":[148],"network":[151,203],"weight":[152],"matrices.":[153],"former":[155],"encounters":[156],"similar":[157],"underfitting":[158],"issues":[159],"as":[160],"mean-field":[161],"approaches,":[163],"which":[164],"alleviated":[167],"by":[168],"MAP-style":[170],"hierarchi-":[174],"cal":[175],"model.":[176],"latter,":[178],"an":[181],"extension":[182],"Matheron\u2019s":[184],"rule":[185],"matrix":[187],"normal":[188],"distributions,":[189],"achieves":[190],"comparable":[191],"ensembles":[196],"with":[197,268,274,286],"accuracy":[199],"deterministic":[202],"using":[205],"only":[206],"25%":[207],"number":[210],"single":[215],"ResNet-50.":[216],"third":[218],"introduces":[220],"TyXe,":[221],"probabilistic":[223],"programming":[224],"library":[225],"built":[226],"top":[228],"Pyro":[230],"facilitate":[232],"turning":[233],"PyTorch":[234],"into":[237,282],"ones.":[239],"In":[240],"contrast":[241],"existing":[243],"frameworks,":[244],"TyXe":[245],"avoids":[246],"introducing":[247],"layer":[249],"abstraction,":[250],"allowing":[251],"it":[252],"support":[254],"arbitrary":[255],"architectures.":[256],"is":[258],"demonstrated":[259],"range":[262],"applications,":[264],"image":[266],"classification":[267],"torchvision":[269],"ResNets":[270],"node":[272],"labelling":[273],"DGL":[275],"graph":[276],"incorporating":[280],"radiance":[284],"fields":[285],"PyTorch3d.":[287]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}