{"id":"https://openalex.org/W2994610548","doi":null,"title":"From Variational to Deterministic Autoencoders","display_name":"From Variational to Deterministic Autoencoders","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W2994610548","mag":"2994610548"},"language":"en","primary_location":{"id":"mag:2994610548","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/journals/corr/corr1903.html#abs-1903-12436","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","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 Learning Representations","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001735719","display_name":"Partha Sarathi Ghosh","orcid":"https://orcid.org/0000-0003-4808-3370","observed_orcids":["https://orcid.org/0000-0003-4808-3370"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Partha Ghosh","raw_affiliation_strings":["Max Planck Society, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4808-3370","affiliations":[{"raw_affiliation_string":"Max Planck Society, Munich, Germany","institution_ids":["https://openalex.org/I149899117"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014641975","display_name":"Mehdi S. M. Sajjadi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehdi S. M. Sajjadi","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069110696","display_name":"Antonio Vergari","orcid":"https://orcid.org/0000-0003-0036-5678","observed_orcids":["https://orcid.org/0000-0003-0036-5678"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Vergari","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, United States"],"raw_orcid":"https://orcid.org/0000-0003-0036-5678","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, United States","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065396778","display_name":"Michael J. Black","orcid":"https://orcid.org/0000-0001-6077-4540","observed_orcids":["https://orcid.org/0000-0001-6077-4540"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael J. Black","raw_affiliation_strings":["Max Planck Society, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6077-4540","affiliations":[{"raw_affiliation_string":"Max Planck Society, Munich, Germany","institution_ids":["https://openalex.org/I149899117"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044005697","display_name":"Bernhard Sch\u00f6lkopf","orcid":"https://orcid.org/0000-0002-8177-0925","observed_orcids":["https://orcid.org/0000-0002-8177-0925"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernhard Sch\u00f6lkopf","raw_affiliation_strings":["Max Planck Society, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8177-0925","affiliations":[{"raw_affiliation_string":"Max Planck Society, Munich, Germany","institution_ids":["https://openalex.org/I149899117"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.0388,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.96086078,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5346999764442444,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5346999764442444,"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"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.1665000021457672,"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/T10028","display_name":"Topic Modeling","score":0.13099999725818634,"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/variational-autoencoder","display_name":"variational autoencoder","score":0.9929999709129333},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.6710000038146973},{"id":"https://openalex.org/keywords/latent-space-regularization","display_name":"latent space regularization","score":0.6579999923706055},{"id":"https://openalex.org/keywords/noise-injection","display_name":"noise injection","score":0.5379999876022339},{"id":"https://openalex.org/keywords/specimen-quality","display_name":"sample quality","score":0.6269999742507935},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.6790000200271606},{"id":"https://openalex.org/keywords/molecular-generation","display_name":"molecular generation","score":0.722000002861023},{"id":"https://openalex.org/keywords/structured-data-generation","display_name":"structured data generation","score":0.7239999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.769390881061554},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6762855052947998},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6378903388977051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5636683702468872},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.503715455532074},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4994943141937256},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47702905535697937},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.47237876057624817},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.46435120701789856},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4603967070579529},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4175460934638977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3724960684776306},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3312610983848572},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2502383589744568},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0997920036315918},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2994610548","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/journals/corr/corr1903.html#abs-1903-12436","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","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 Learning Representations","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1779483307","https://openalex.org/W1834627138","https://openalex.org/W1836465849","https://openalex.org/W1866230956","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2025768430","https://openalex.org/W2070665556","https://openalex.org/W2099057450","https://openalex.org/W2099471712","https://openalex.org/W2102862543","https://openalex.org/W2112796928","https://openalex.org/W2124136621","https://openalex.org/W2131686485","https://openalex.org/W2134842679","https://openalex.org/W2135181320","https://openalex.org/W2149846618","https://openalex.org/W2188365844","https://openalex.org/W2210838531","https://openalex.org/W2529996553","https://openalex.org/W2537458122","https://openalex.org/W2552465432","https://openalex.org/W2560512785","https://openalex.org/W2586756136","https://openalex.org/W2594057160","https://openalex.org/W2602076750","https://openalex.org/W2613715972","https://openalex.org/W2739748921","https://openalex.org/W2753738274","https://openalex.org/W2768599997","https://openalex.org/W2785678896","https://openalex.org/W2786722833","https://openalex.org/W2788017640","https://openalex.org/W2792263949","https://openalex.org/W2805984778","https://openalex.org/W2843598537","https://openalex.org/W2893749619","https://openalex.org/W2898272469","https://openalex.org/W2911290044","https://openalex.org/W2947590261","https://openalex.org/W2950220847","https://openalex.org/W2962738009","https://openalex.org/W2962879692","https://openalex.org/W2963034614","https://openalex.org/W2963145887","https://openalex.org/W2963467180","https://openalex.org/W2963676163","https://openalex.org/W2963799213","https://openalex.org/W2963981733","https://openalex.org/W2964137095","https://openalex.org/W7097137556"],"related_works":["https://openalex.org/W4281264290","https://openalex.org/W3090228367","https://openalex.org/W3009765449","https://openalex.org/W4226299691","https://openalex.org/W2906670434","https://openalex.org/W7117751704","https://openalex.org/W7104252761","https://openalex.org/W2911290044","https://openalex.org/W3043880067","https://openalex.org/W3187179100"],"abstract_inverted_index":{"Variational":[0],"Autoencoders":[1],"(VAEs)":[2],"provide":[3],"a":[4,15,60,64,78,120,156],"theoretically-backed":[5],"and":[6,24,45,92,102,181],"popular":[7],"framework":[8,35,143],"for":[9,36],"deep":[10],"generative":[11,37,121],"models.":[12],"However,":[13],"learning":[14],"VAE":[16,66],"from":[17],"data":[18,126,194],"poses":[19],"still":[20],"unanswered":[21],"theoretical":[22],"questions":[23],"considerable":[25],"practical":[26],"challenges.":[27],"In":[28],"this":[29,85],"work,":[30],"we":[31,128],"propose":[32],"an":[33,99,114,130],"alternative":[34],"modeling":[38],"that":[39,58,135,160,171],"is":[40],"simpler,":[41],"easier":[42],"to":[43,98,108,111,113,123,140,168,187,192],"train,":[44],"deterministic,":[46],"yet":[47],"has":[48],"many":[49],"of":[50,53,77,87,179],"the":[51,54,75,141,161],"advantages":[52],"VAE.":[55],"We":[56,81,153],"observe":[57],"sampling":[59],"stochastic":[61],"encoder":[62],"in":[63,155],"Gaussian":[65],"can":[67,96,136],"be":[68,137],"interpreted":[69],"as":[70,144,146,189,191,196],"simply":[71],"injecting":[72],"noise":[73],"into":[74],"input":[76],"deterministic":[79,164],"decoder.":[80],"investigate":[82],"how":[83],"substituting":[84],"kind":[86],"stochasticity,":[88],"with":[89],"other":[90],"explicit":[91],"implicit":[93],"regularization":[94],"schemes,":[95],"lead":[97],"equally":[100],"smooth":[101],"meaningful":[103],"latent":[104],"space":[105],"without":[106],"having":[107],"force":[109],"it":[110],"conform":[112],"arbitrarily":[115],"chosen":[116],"prior.":[117],"To":[118],"retrieve":[119],"mechanism":[122],"sample":[124,151],"new":[125],"points,":[127],"introduce":[129],"ex-post":[131],"density":[132],"estimation":[133],"step":[134],"readily":[138],"applied":[139,186],"proposed":[142,162],"well":[145,190],"existing":[147],"VAEs,":[148],"improving":[149],"their":[150],"quality.":[152],"show,":[154],"rigorous":[157],"empirical":[158],"study,":[159],"regularized":[163],"autoencoders":[165],"are":[166,172],"able":[167],"generate":[169],"samples":[170],"comparable":[173],"to,":[174],"or":[175],"better":[176],"than,":[177],"those":[178],"VAEs":[180],"more":[182],"powerful":[183],"alternatives":[184],"when":[185],"images":[188],"structured":[193],"such":[195],"molecules.":[197]},"counts_by_year":[{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":5}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-12-26T00:00:00"}