{"id":"https://openalex.org/W4283034593","doi":"https://doi.org/10.48550/arxiv.2206.07235","title":"Training Discrete Deep Generative Models via Gapped Straight-Through Estimator","display_name":"Training Discrete Deep Generative Models via Gapped Straight-Through Estimator","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4283034593","doi":"https://doi.org/10.48550/arxiv.2206.07235"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2206.07235","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":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2206.07235","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085851733","display_name":"Ting-Han Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Ting-Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054133264","display_name":"Ta-Chung Chi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi, Ta-Chung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040668817","display_name":"Alexander I. Rudnicky","orcid":"https://orcid.org/0000-0003-2044-8446"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rudnicky, Alexander I.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041274293","display_name":"Peter J. Ramadge","orcid":"https://orcid.org/0000-0002-3282-216X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramadge, Peter J.","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"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":1,"citation_normalized_percentile":{"value":0.659251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":60,"max":70},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9983,"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":0.9983,"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/T11309","display_name":"Music and Audio Processing","score":0.9803,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11448","display_name":"Face recognition and analysis","score":0.9757,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.7387756},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.5805996},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.45803857}],"concepts":[{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.7387756},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.71058726},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5917896},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.5805996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.53801674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5304541},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4794875},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.45803857},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43083942},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40323246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34216166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34079558},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.28366435},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28191367},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22510523},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2206.07235","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":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2206.07235","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2206.07235","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":["Cornell University"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Quality education","score":0.53,"id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4283319738","https://openalex.org/W3034780828","https://openalex.org/W2900543860","https://openalex.org/W2298254442","https://openalex.org/W2291558465","https://openalex.org/W2169816622","https://openalex.org/W2169367269","https://openalex.org/W2135002170","https://openalex.org/W1997242758","https://openalex.org/W1981992409"],"abstract_inverted_index":{"While":[0],"deep":[1,111],"generative":[2,112],"models":[3],"have":[4],"succeeded":[5],"in":[6,40],"image":[7],"processing,":[8,11],"natural":[9],"language":[10],"and":[12,50,84,116],"reinforcement":[13],"learning,":[14],"training":[15],"that":[16,90,96],"involves":[17,47],"discrete":[18,110],"random":[19],"variables":[20],"remains":[21],"challenging":[22],"due":[23],"to":[24,61,105],"the":[25,63,74,97],"high":[26],"variance":[27,42,64],"of":[28,77],"its":[29],"gradient":[30],"estimation":[31],"process.":[32],"Monte":[33],"Carlo":[34],"is":[35,71],"a":[36,56],"common":[37],"solution":[38],"used":[39],"most":[41],"reduction":[43],"approaches.":[44],"However,":[45],"this":[46],"time-consuming":[48],"resampling":[49,67],"multiple":[51],"function":[52],"evaluations.":[53],"We":[54,80],"propose":[55],"Gapped":[57],"Straight-Through":[58,78],"(GST)":[59],"estimator":[60,70,100],"reduce":[62],"without":[65],"incurring":[66],"overhead.":[68],"This":[69],"inspired":[72],"by":[73],"essential":[75],"properties":[76,83],"Gumbel-Softmax.":[79],"determine":[81],"these":[82],"show":[85],"via":[86],"an":[87],"ablation":[88],"study":[89],"they":[91],"are":[92],"essential.":[93],"Experiments":[94],"demonstrate":[95],"proposed":[98],"GST":[99],"enjoys":[101],"better":[102],"performance":[103],"compared":[104],"strong":[106],"baselines":[107],"on":[108],"two":[109],"modeling":[113],"tasks,":[114],"MNIST-VAE":[115],"ListOps.":[117]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4283034593","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-01-06T05:15:00.194639","created_date":"2022-06-18"}