{"id":"https://openalex.org/W2950312925","doi":null,"title":"Improving Importance Weighted Auto-Encoders with Annealed Importance Sampling.","display_name":"Improving Importance Weighted Auto-Encoders with Annealed Importance Sampling.","publication_year":2019,"publication_date":"2019-06-12","ids":{"openalex":"https://openalex.org/W2950312925","mag":"2950312925"},"language":"en","primary_location":{"id":"mag:2950312925","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1906.04904","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/1906.04904","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027230160","display_name":"Xinqiang Ding","orcid":"https://orcid.org/0000-0002-4598-8732","observed_orcids":["https://orcid.org/0000-0002-4598-8732"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinqiang Ding","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4598-8732","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066814691","display_name":"David J. Freedman","orcid":"https://orcid.org/0000-0002-2485-5981","observed_orcids":["https://orcid.org/0000-0002-2485-5981"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David J. Freedman","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2485-5981","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":3,"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":0.8574000000953674,"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":0.8574000000953674,"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":0.10859999805688858,"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/T10028","display_name":"Topic Modeling","score":0.008799999952316284,"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/annealed-importance-sampling","display_name":"annealed importance sampling","score":0.9950000047683716},{"id":"https://openalex.org/keywords/latent-variable-modeling","display_name":"latent variable models","score":0.7649999856948853},{"id":"https://openalex.org/keywords/variational-bayesian-inference","display_name":"variational inference","score":0.7739999890327454},{"id":"https://openalex.org/keywords/amortized-inference","display_name":"amortized inference","score":0.8600000143051147},{"id":"https://openalex.org/keywords/latent-representations","display_name":"latent representations","score":0.5770000219345093},{"id":"https://openalex.org/keywords/density-estimation","display_name":"density estimation","score":0.5920000076293945}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7424829602241516},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6603142023086548},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5880205035209656},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5531594753265381},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.5257059931755066},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4797324240207672},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47840890288352966},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4562895894050598},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41918861865997314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4117376208305359},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37611860036849976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3425444960594177},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15445220470428467},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2950312925","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1906.04904","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2950312925","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1906.04904","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1481935768","https://openalex.org/W1513873506","https://openalex.org/W1906598733","https://openalex.org/W1985093013","https://openalex.org/W2056760934","https://openalex.org/W2112796928","https://openalex.org/W2120340025","https://openalex.org/W2135354436","https://openalex.org/W2138309709","https://openalex.org/W2166851633","https://openalex.org/W2194321275","https://openalex.org/W2567948266","https://openalex.org/W2739517340","https://openalex.org/W2806061475","https://openalex.org/W6977390765"],"related_works":["https://openalex.org/W2973674981","https://openalex.org/W1779483307","https://openalex.org/W3155990531","https://openalex.org/W2964275204","https://openalex.org/W2764301726","https://openalex.org/W3006615586","https://openalex.org/W1959608418","https://openalex.org/W2785443624","https://openalex.org/W2921682319","https://openalex.org/W4306178101"],"abstract_inverted_index":{"Stochastic":[0],"variational":[1,41],"inference":[2,6],"with":[3,88],"an":[4,109],"amortized":[5],"model":[7],"and":[8,54,85,93,152],"the":[9,23,36,50,69,89,100,115,118,122,139],"reparameterization":[10],"trick":[11],"has":[12,125],"become":[13],"a":[14,65],"widely-used":[15],"algorithm":[16],"for":[17,75],"learning":[18,67,76],"latent":[19,77,119,155],"variable":[20,78],"models.":[21,79],"Increasing":[22],"flexibility":[24],"of":[25,35,45,102,117],"approximate":[26],"posterior":[27,123,150],"distributions":[28,151],"while":[29],"maintaining":[30],"computational":[31,129],"tractability":[32],"is":[33],"one":[34],"core":[37],"problems":[38],"in":[39,112],"stochastic":[40],"inference.":[42],"Two":[43],"families":[44],"approaches":[46,56,87],"proposed":[47,81],"to":[48,135],"address":[49],"problem":[51],"are":[52,143],"flow-based":[53,86],"multisample-based":[55,84],"such":[57],"as":[58],"importance":[59,71,91],"weighted":[60,72],"auto-encoders":[61],"(IWAE).":[62],"We":[63],"introduce":[64],"new":[66],"algorithm,":[68],"annealed":[70,90],"auto-encoder":[73],"(AIWAE),":[74],"The":[80,105],"AIWAE":[82,113],"combines":[83],"sampling":[92],"its":[94],"memory":[95],"cost":[96],"stays":[97],"constant":[98],"when":[99,121],"depth":[101],"flows":[103],"increases.":[104],"flow":[106],"constructed":[107],"using":[108,138],"annealing":[110],"process":[111],"facilitates":[114],"exploration":[116],"space":[120,156],"distribution":[124],"multiple":[126],"modes.":[127],"Through":[128],"experiments,":[130],"we":[131],"show":[132],"that,":[133],"compared":[134],"models":[136,142],"trained":[137],"IWAE,":[140],"AIWAE-trained":[141],"better":[144],"density":[145],"models,":[146],"have":[147],"more":[148,154],"complex":[149],"use":[153],"representation":[157],"capacity.":[158]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-06-27T00:00:00"}