{"id":"https://openalex.org/W4415798196","doi":"https://doi.org/10.52202/079017-1296","title":"Improved Sample Complexity Bounds for Diffusion Model Training","display_name":"Improved Sample Complexity Bounds for Diffusion Model Training","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415798196","doi":"https://doi.org/10.52202/079017-1296"},"language":"en","primary_location":{"id":"doi:10.52202/079017-1296","doi":"https://doi.org/10.52202/079017-1296","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-1296","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.13745","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023290544","display_name":"Shivam Gupta","orcid":"https://orcid.org/0000-0002-2714-4958","observed_orcids":["https://orcid.org/0000-0002-2714-4958","https://orcid.org/0009-0006-3463-3967"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shivam Gupta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039707395","display_name":"Aditya Parulekar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditya Parulekar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083990461","display_name":"Eric Price","orcid":"https://orcid.org/0000-0002-3480-8054","observed_orcids":["https://orcid.org/0000-0002-3480-8054"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Price","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018982736","display_name":"Zhiyang Xun","orcid":"https://orcid.org/0009-0000-6394-0436","observed_orcids":["https://orcid.org/0009-0000-6394-0436"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyang Xun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5606,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72935277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"40976","last_page":"41012"},"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":0.9160000085830688,"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":0.9160000085830688,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.04270000010728836,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.007000000216066837,"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/diffusion-models","display_name":"diffusion models","score":0.968999981880188},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.9850000143051147},{"id":"https://openalex.org/keywords/training-complexity","display_name":"training complexity","score":0.5360000133514404},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.6589999794960022},{"id":"https://openalex.org/keywords/neural-network-depth","display_name":"neural network depth","score":0.5669999718666077},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.5720000267028809}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4708000123500824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42570000886917114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41990000009536743},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.41589999198913574},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31200000643730164},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3095000088214874},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-1296","doi":"https://doi.org/10.52202/079017-1296","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-1296","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2311.13745","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.13745","pdf_url":"https://arxiv.org/pdf/2311.13745","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.13745","doi":"https://doi.org/10.48550/arxiv.2311.13745","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.13745","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.13745","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.13745","pdf_url":"https://arxiv.org/pdf/2311.13745","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1200718643","display_name":"CAREER: Fundamental Algorithms for Data-Limited Problems","funder_award_id":"1751040","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415798196.pdf","grobid_xml":"https://content.openalex.org/works/W4415798196.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W3003409689"],"related_works":["https://openalex.org/W6908459910","https://openalex.org/W4415330138","https://openalex.org/W4407633238","https://openalex.org/W7021146773","https://openalex.org/W4415798575","https://openalex.org/W7090709548","https://openalex.org/W7125965803","https://openalex.org/W4415800709","https://openalex.org/W4405469853","https://openalex.org/W4406779567"],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"have":[2,31],"become":[3],"the":[4,33,52,83,98],"most":[5],"popular":[6],"approach":[7],"to":[8,16,40,65],"deep":[9],"generative":[10],"modeling":[11],"of":[12,28,36,55],"images,":[13],"largely":[14],"due":[15],"their":[17],"empirical":[18],"performance":[19],"and":[20,89,103],"reliability.":[21],"From":[22],"a":[23,26,58,72],"theoretical":[24],"standpoint,":[25],"number":[27],"recent":[29],"works":[30],"studied":[32],"iteration":[34],"complexity":[35,54],"sampling,":[37],"assuming":[38],"access":[39],"an":[41,67,94],"accurate":[42,68],"diffusion":[43,69],"model.":[44],"In":[45],"this":[46],"work,":[47],"we":[48],"focus":[49],"on":[50,100,109],"understanding":[51],"sample":[53],"training":[56],"such":[57],"model;":[59],"how":[60],"many":[61],"samples":[62],"are":[63],"needed":[64],"learn":[66],"model":[70],"using":[71],"sufficiently":[73],"expressive":[74],"neural":[75],"network?":[76],"Prior":[77],"work":[78],"showed":[79],"bounds":[80],"polynomial":[81],"in":[82,97],"dimension,":[84],"desired":[85],"Total":[86],"Variation":[87],"error,":[88],"Wasserstein":[90,101],"error.":[91],"We":[92],"show":[93],"exponential":[95],"improvement":[96],"dependence":[99],"error":[102],"depth,":[104],"along":[105],"with":[106],"improved":[107],"dependencies":[108],"other":[110],"relevant":[111],"parameters.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-11-03T00:00:00"}