{"id":"https://openalex.org/W2804766086","doi":"https://doi.org/10.48550/arxiv.1806.01851","title":"Pathwise Derivatives Beyond the Reparameterization Trick","display_name":"Pathwise Derivatives Beyond the Reparameterization Trick","publication_year":2018,"publication_date":"2018-06-05","ids":{"openalex":"https://openalex.org/W2804766086","doi":"https://doi.org/10.48550/arxiv.1806.01851","mag":"2804766086"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1806.01851","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.01851","pdf_url":"https://arxiv.org/pdf/1806.01851","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.01851","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054350362","display_name":"Martin Jankowiak","orcid":"https://orcid.org/0000-0002-1724-0436","observed_orcids":["https://orcid.org/0000-0002-1724-0436"]},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jankowiak, Martin","raw_affiliation_strings":["Uber AI Labs , San Francisco , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uber AI Labs , San Francisco , USA","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091084994","display_name":"Fritz H. Obermeyer","orcid":"https://orcid.org/0000-0003-2850-4991","observed_orcids":["https://orcid.org/0000-0003-2850-4991"]},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Obermeyer, Fritz","raw_affiliation_strings":["Uber AI Labs , San Francisco , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uber AI Labs , San Francisco , USA","institution_ids":["https://openalex.org/I2946016260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2946016260"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2235","last_page":"2244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9609000086784363,"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":0.9609000086784363,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.01730000041425228,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0071000000461936,"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/reparameterization-trick","display_name":"reparameterization trick","score":0.9860000014305115},{"id":"https://openalex.org/keywords/optimal-transport","display_name":"optimal transport","score":0.9480000138282776},{"id":"https://openalex.org/keywords/transport-equation","display_name":"transport equation","score":0.9610000252723694},{"id":"https://openalex.org/keywords/stochastic-variational-inference","display_name":"stochastic variational inference","score":0.824999988079071},{"id":"https://openalex.org/keywords/gradient-variance-reduction","display_name":"gradient variance reduction","score":0.703000009059906},{"id":"https://openalex.org/keywords/gamma-distribution","display_name":"gamma distribution","score":0.699999988079071},{"id":"https://openalex.org/keywords/beta-distribution","display_name":"beta distribution","score":0.9980000257492065},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":1.0},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.8389999866485596},{"id":"https://openalex.org/keywords/multivariate-normal-distribution","display_name":"multivariate normal distribution","score":0.847000002861023},{"id":"https://openalex.org/keywords/gaussian-process-regression","display_name":"Gaussian process regression","score":0.8970000147819519}],"concepts":[{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.47687584161758423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37311220169067383},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3324369788169861},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.327605277299881},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3231176733970642}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1806.01851","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.01851","pdf_url":"https://arxiv.org/pdf/1806.01851","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,"listed_in":[],"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":"doi:10.48550/arxiv.1806.01851","doi":"https://doi.org/10.48550/arxiv.1806.01851","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.01851","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,"listed_in":[],"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"},{"id":"mag:2963916785","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v80/jankowiak18a/jankowiak18a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1806.01851","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.01851","pdf_url":"https://arxiv.org/pdf/1806.01851","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2804766086.pdf","grobid_xml":"https://content.openalex.org/works/W2804766086.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1502922572","https://openalex.org/W1516111018","https://openalex.org/W1522579744","https://openalex.org/W1585160083","https://openalex.org/W1646152356","https://openalex.org/W1729198099","https://openalex.org/W1909320841","https://openalex.org/W1919588359","https://openalex.org/W1959608418","https://openalex.org/W1994616650","https://openalex.org/W2034376463","https://openalex.org/W2046765929","https://openalex.org/W2077788215","https://openalex.org/W2116059849","https://openalex.org/W2119196781","https://openalex.org/W2119717200","https://openalex.org/W2122262818","https://openalex.org/W2146502635","https://openalex.org/W2150807068","https://openalex.org/W2153185114","https://openalex.org/W2166851633","https://openalex.org/W2290226688","https://openalex.org/W2331747324","https://openalex.org/W2495475966","https://openalex.org/W2531823172","https://openalex.org/W2602076750","https://openalex.org/W2619251062","https://openalex.org/W2767002724","https://openalex.org/W2899771611","https://openalex.org/W2952264928","https://openalex.org/W2963557175","https://openalex.org/W2963811225","https://openalex.org/W2964121744","https://openalex.org/W2964260519"],"related_works":["https://openalex.org/W2806981709","https://openalex.org/W2963557175","https://openalex.org/W2531823172","https://openalex.org/W4414829955","https://openalex.org/W3157722551","https://openalex.org/W3099280155","https://openalex.org/W7221058420","https://openalex.org/W2619251062","https://openalex.org/W2910314774","https://openalex.org/W2909082183"],"abstract_inverted_index":{"We":[0,25,48,75,93],"observe":[1,50],"that":[2,51,82,106],"gradients":[3,33,66,79,109],"computed":[4],"via":[5],"the":[6,16,20,41,53,59,64,70,77],"reparameterization":[7,42,54],"trick":[8,55],"are":[9,67,110],"in":[10,19,69,87],"direct":[11],"correspondence":[12],"with":[13,95,112],"solutions":[14],"of":[15,22,72,98],"transport":[17],"equation":[18],"formalism":[21],"optimal":[23,73,78],"transport.":[24,74],"use":[26],"this":[27],"perspective":[28],"to":[29,40,58],"compute":[30],"(approximate)":[31],"pathwise":[32,108],"for":[34],"probability":[35],"distributions":[36],"not":[37],"directly":[38],"amenable":[39],"trick:":[43],"Gamma,":[44],"Beta,":[45],"and":[46,80,101],"Dirichlet.":[47],"further":[49],"when":[52],"is":[56],"applied":[57],"Cholesky-factorized":[60],"multivariate":[61],"Normal":[62],"distribution,":[63],"resulting":[65],"suboptimal":[68],"sense":[71],"derive":[76],"show":[81],"they":[83],"have":[84],"reduced":[85],"variance":[86],"a":[88,96],"Gaussian":[89],"Process":[90],"regression":[91],"task.":[92],"demonstrate":[94],"variety":[97],"synthetic":[99],"experiments":[100],"stochastic":[102],"variational":[103],"inference":[104],"tasks":[105],"our":[107],"competitive":[111],"other":[113],"methods.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-06-01T00:00:00"}