{"id":"https://openalex.org/W3010729701","doi":null,"title":"KALE: When Energy-Based Learning Meets Adversarial Training.","display_name":"KALE: When Energy-Based Learning Meets Adversarial Training.","publication_year":2020,"publication_date":"2020-03-10","ids":{"openalex":"https://openalex.org/W3010729701","mag":"3010729701"},"language":"en","primary_location":{"id":"mag:3010729701","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/journals/corr/corr2003.html#abs-2003-05033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","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/A5054854070","display_name":"Michael Arbel","orcid":"https://orcid.org/0000-0002-6946-4327","observed_orcids":["https://orcid.org/0000-0002-6946-4327"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Arbel","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6946-4327","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110743685","display_name":"Zhou Liang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004160420","display_name":"Arthur Gretton","orcid":"https://orcid.org/0000-0003-3169-7624","observed_orcids":["https://orcid.org/0000-0003-3169-7624"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arthur Gretton","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3169-7624","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4218,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.57629893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":96},"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":0.9682999849319458,"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":0.9682999849319458,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.012900000438094139,"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":0.003599999938160181,"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/energy-based-models","display_name":"energy-based models","score":0.7799999713897705},{"id":"https://openalex.org/keywords/generative-modelling","display_name":"generative modelling","score":0.8629999756813049},{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.8320000171661377},{"id":"https://openalex.org/keywords/energy-function","display_name":"energy function","score":0.6710000038146973},{"id":"https://openalex.org/keywords/mcmc-sampling","display_name":"MCMC sampling","score":0.7419999837875366},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.9610000252723694},{"id":"https://openalex.org/keywords/density-estimation","display_name":"density estimation","score":0.8109999895095825},{"id":"https://openalex.org/keywords/normalizing-flows","display_name":"normalizing flows","score":0.8949999809265137},{"id":"https://openalex.org/keywords/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.7089999914169312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6516844034194946},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.6325552463531494},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6024789214134216},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.586754560470581},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5606067180633545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5481940507888794},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5208585858345032},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5165539979934692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4442732632160187},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4229191243648529},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24411162734031677},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24205145239830017},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.074128657579422},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3010729701","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/journals/corr/corr2003.html#abs-2003-05033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"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":40,"referenced_works":["https://openalex.org/W1653619892","https://openalex.org/W1866230956","https://openalex.org/W1942833897","https://openalex.org/W1959608418","https://openalex.org/W2069663974","https://openalex.org/W2099471712","https://openalex.org/W2113642685","https://openalex.org/W2116064496","https://openalex.org/W2120340025","https://openalex.org/W2126574351","https://openalex.org/W2129462326","https://openalex.org/W2155193980","https://openalex.org/W2164452299","https://openalex.org/W2166944917","https://openalex.org/W2173520492","https://openalex.org/W2296616510","https://openalex.org/W2419501139","https://openalex.org/W2592172378","https://openalex.org/W2593729559","https://openalex.org/W2617322972","https://openalex.org/W2739748921","https://openalex.org/W2768400049","https://openalex.org/W2777497231","https://openalex.org/W2785678896","https://openalex.org/W2803117117","https://openalex.org/W2897371726","https://openalex.org/W2945125725","https://openalex.org/W2950735465","https://openalex.org/W2962771722","https://openalex.org/W2962818398","https://openalex.org/W2962879692","https://openalex.org/W2962919088","https://openalex.org/W2963295938","https://openalex.org/W2963972841","https://openalex.org/W2963981733","https://openalex.org/W2970607325","https://openalex.org/W2970938715","https://openalex.org/W2995289379","https://openalex.org/W3011675874","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W3035326363","https://openalex.org/W4312496688","https://openalex.org/W2922772346","https://openalex.org/W2970607325","https://openalex.org/W2962775818","https://openalex.org/W2521028896","https://openalex.org/W6891855720","https://openalex.org/W7213264264","https://openalex.org/W3129261417","https://openalex.org/W4386651302"],"abstract_inverted_index":{"We":[0,86],"introduce":[1],"the":[2,27,46,50,54,61,69,81,84,94,104,113,117,120,124,144,158,168,175,199],"Generalized":[3],"Energy":[4],"Based":[5],"Model":[6],"(GEBM)":[7],"for":[8,111],"generative":[9],"modelling.":[10],"These":[11],"models":[12],"combine":[13],"two":[14],"trained":[15,76,125],"components:":[16],"a":[17,36,100,172],"base":[18,58,70,183],"distribution":[19,71],"(generally":[20],"an":[21,41],"implicit":[22],"model),":[23],"which":[24,66],"can":[25,127],"learn":[26],"support":[28],"of":[29,123,151,174,198],"data":[30],"with":[31],"low":[32],"intrinsic":[33],"dimension":[34],"in":[35,135],"high":[37],"dimensional":[38],"space;":[39],"and":[40,57,83,103],"energy":[42,55,82,95],"function,":[43],"to":[44,194],"refine":[45],"probability":[47],"mass":[48],"on":[49,119,147,187],"learned":[51,97,159],"support.":[52],"Both":[53],"function":[56],"jointly":[59],"constitute":[60],"final":[62],"model,":[63],"unlike":[64],"GANs,":[65],"retain":[67],"only":[68],"(the":[72],"generator).":[73],"GEBMs":[74,185],"are":[75,92,150],"by":[77,98],"alternating":[78],"between":[79],"learning":[80,112],"base.":[85,114],"show":[87],"that":[88,138,163],"both":[89],"training":[90],"stages":[91],"well-defined:":[93],"is":[96],"maximising":[99],"generalized":[101],"likelihood,":[102],"resulting":[105],"energy-based":[106],"loss":[107],"provides":[108],"informative":[109],"gradients":[110],"Samples":[115],"from":[116,157],"posterior":[118],"latent":[121],"space":[122,137],"model":[126],"be":[128],"obtained":[129],"via":[130],"MCMC,":[131],"thus":[132],"finding":[133],"regions":[134],"this":[136],"produce":[139],"better":[140,153],"quality":[141,154],"samples.":[142],"Empirically,":[143],"GEBM":[145,169],"samples":[146],"image-generation":[148],"tasks":[149],"much":[152],"than":[155],"those":[156],"generator":[160],"alone,":[161],"indicating":[162],"all":[164],"else":[165],"being":[166],"equal,":[167],"will":[170],"outperform":[171],"GAN":[173],"same":[176,200],"complexity.":[177],"When":[178],"using":[179],"normalizing":[180],"flows":[181],"as":[182],"measures,":[184],"succeed":[186],"density":[188],"modelling":[189],"tasks,":[190],"returning":[191],"comparable":[192],"performance":[193],"direct":[195],"maximum":[196],"likelihood":[197],"networks.":[201]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-03-23T00:00:00"}