{"id":"https://openalex.org/W2825557436","doi":"https://doi.org/10.23919/isita.2018.8664326","title":"Fast yet Simple Natural-Gradient Descent for Variational Inference in Complex Models","display_name":"Fast yet Simple Natural-Gradient Descent for Variational Inference in Complex Models","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2825557436","doi":"https://doi.org/10.23919/isita.2018.8664326","mag":"2825557436"},"language":"en","primary_location":{"id":"doi:10.23919/isita.2018.8664326","is_oa":false,"landing_page_url":"https://doi.org/10.23919/isita.2018.8664326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Symposium on Information Theory and Its Applications (ISITA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1807.04489","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053565482","display_name":"Mohammad Emtiyaz Khan","orcid":"https://orcid.org/0000-0001-7614-0489"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mohammad Emtiyaz Khan","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019269745","display_name":"Didrik Nielsen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Didrik Nielsen","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053565482"],"corresponding_institution_ids":["https://openalex.org/I4210126580"],"apc_list":null,"apc_paid":null,"fwci":0.3385,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68119748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9983000159263611,"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":0.998199999332428,"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/gradient-descent","display_name":"Gradient descent","score":0.7368788719177246},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7338847517967224},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.6217716932296753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6042556762695312},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5826399326324463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5386185050010681},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.506801187992096},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.49976515769958496},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4533114731311798},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4427409768104553},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4397229254245758},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41367584466934204},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3782762885093689},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3237132430076599}],"concepts":[{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.7368788719177246},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7338847517967224},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.6217716932296753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6042556762695312},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5826399326324463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5386185050010681},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.506801187992096},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.49976515769958496},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4533114731311798},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4427409768104553},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4397229254245758},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41367584466934204},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3782762885093689},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3237132430076599},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.23919/isita.2018.8664326","is_oa":false,"landing_page_url":"https://doi.org/10.23919/isita.2018.8664326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Symposium on Information Theory and Its Applications (ISITA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1807.04489","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.04489","pdf_url":"https://arxiv.org/pdf/1807.04489","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2825557436","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1807.04489","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1807.04489","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1807.04489","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1807.04489","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.04489","pdf_url":"https://arxiv.org/pdf/1807.04489","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335125","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2825557436.pdf","grobid_xml":"https://content.openalex.org/works/W2825557436.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1970789124","https://openalex.org/W2034376463","https://openalex.org/W2119717200","https://openalex.org/W2485135680","https://openalex.org/W6631190155","https://openalex.org/W6639732818","https://openalex.org/W6640231202","https://openalex.org/W6640963894","https://openalex.org/W6675528826","https://openalex.org/W6676315081","https://openalex.org/W6678397451","https://openalex.org/W6680270327","https://openalex.org/W6680851092","https://openalex.org/W6682648773","https://openalex.org/W6684578138","https://openalex.org/W6735905430","https://openalex.org/W6750067904","https://openalex.org/W6764214684"],"related_works":["https://openalex.org/W2964112095","https://openalex.org/W2056918952","https://openalex.org/W2962733101","https://openalex.org/W3184211235","https://openalex.org/W2963798377","https://openalex.org/W2991114314","https://openalex.org/W2161829742","https://openalex.org/W3153112662","https://openalex.org/W2971678291","https://openalex.org/W2785391921","https://openalex.org/W2153185114","https://openalex.org/W2743798057","https://openalex.org/W2944919463","https://openalex.org/W2618164330","https://openalex.org/W2949636769","https://openalex.org/W3162611207","https://openalex.org/W3180014105","https://openalex.org/W2801896452","https://openalex.org/W3132174721","https://openalex.org/W3021192559"],"abstract_inverted_index":{"Bayesian":[0,31,115],"inference":[1,25,32],"plays":[2],"an":[3,34],"important":[4],"role":[5],"in":[6,48],"advancing":[7],"machine":[8],"learning,":[9],"but":[10],"faces":[11],"computational":[12],"challenges":[13,28],"when":[14],"applied":[15],"to":[16,72,101],"complex":[17],"models":[18],"such":[19],"as":[20,33],"deep":[21,116],"neural":[22],"networks.":[23],"Variational":[24],"circumvents":[26],"these":[27,91],"by":[29,61,79,95],"formulating":[30],"optimization":[35],"problem":[36],"and":[37],"solving":[38],"it":[39],"using":[40,80,96],"gradient-based":[41,56],"optimization.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"argue":[47],"favor":[49],"of":[50,66,90,121],"natural-gradient":[51,77,122],"approaches":[52,123],"which,":[53],"unlike":[54],"their":[55,125],"counterparts,":[57],"can":[58],"improve":[59],"convergence":[60],"exploiting":[62],"the":[63,67,119],"information":[64],"geometry":[65],"solutions.":[68],"We":[69,110],"show":[70],"how":[71],"derive":[73],"fast":[74],"yet":[75],"simple":[76],"updates":[78],"a":[81],"duality":[82],"associated":[83],"with":[84],"exponential-family":[85],"distributions.":[86],"An":[87],"attractive":[88],"feature":[89],"methods":[92],"is":[93],"that,":[94],"natural-gradients,":[97],"they":[98],"are":[99],"able":[100],"extract":[102],"accurate":[103],"local":[104],"approximations":[105],"for":[106,114],"individual":[107],"model":[108],"components.":[109],"summarize":[111],"recent":[112],"results":[113],"learning":[117],"showing":[118],"superiority":[120],"over":[124],"gradient":[126],"counterparts.":[127]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}