{"id":"https://openalex.org/W4405908601","doi":"https://doi.org/10.1109/itw61385.2024.10807035","title":"Score Matching with Deep Neural Networks: A Non-Asymptotic Analysis","display_name":"Score Matching with Deep Neural Networks: A Non-Asymptotic Analysis","publication_year":2024,"publication_date":"2024-11-24","ids":{"openalex":"https://openalex.org/W4405908601","doi":"https://doi.org/10.1109/itw61385.2024.10807035"},"language":"en","primary_location":{"id":"doi:10.1109/itw61385.2024.10807035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itw61385.2024.10807035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Information Theory Workshop (ITW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5022549732","display_name":"Evan Scope Crafts","orcid":"https://orcid.org/0000-0002-6381-9182"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Evan Scope Crafts","raw_affiliation_strings":["Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin,Austin,TX,USA,78712"],"affiliations":[{"raw_affiliation_string":"Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin,Austin,TX,USA,78712","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102873564","display_name":"Xianyang Zhang","orcid":"https://orcid.org/0000-0002-2512-1816"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianyang Zhang","raw_affiliation_strings":["Texas A&M University,Department of Statistics,College Station,TX,USA,77843"],"affiliations":[{"raw_affiliation_string":"Texas A&M University,Department of Statistics,College Station,TX,USA,77843","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060182809","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0002-3475-8739"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["Oden Institute, The University of Texas at Austin,Department of Biomedical Engineering,Austin,TX,USA,78712"],"affiliations":[{"raw_affiliation_string":"Oden Institute, The University of Texas at Austin,Department of Biomedical Engineering,Austin,TX,USA,78712","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022549732"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22593305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7156999707221985,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7156999707221985,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.6607999801635742,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6237267255783081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6074385046958923},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5646926164627075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.537814736366272},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4407414495944977},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22765305638313293},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21637627482414246}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6237267255783081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6074385046958923},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5646926164627075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.537814736366272},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4407414495944977},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22765305638313293},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21637627482414246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itw61385.2024.10807035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itw61385.2024.10807035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Information Theory Workshop (ITW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2725764100","display_name":null,"funder_award_id":"NIH-R00-EB027181,NIH-R01-GM144351","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6916873942","display_name":null,"funder_award_id":"NSF DMS2113359","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"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1505878979","https://openalex.org/W1536252645","https://openalex.org/W2013035813","https://openalex.org/W2063368770","https://openalex.org/W2524449277","https://openalex.org/W4251232133","https://openalex.org/W4401723506","https://openalex.org/W6628836592","https://openalex.org/W6739659843","https://openalex.org/W6762871372","https://openalex.org/W6765775151","https://openalex.org/W6779823529","https://openalex.org/W6795288823","https://openalex.org/W6803078664","https://openalex.org/W6845080539"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Score":[0],"matching":[1,58,88],"is":[2,50,67,82],"a":[3,16,24,36,68],"statistical":[4],"approach":[5,99],"for":[6,113],"estimating":[7],"the":[8,13,40,56,61,64,76,79,86,92,95,136,140,147,154],"score":[9,57,65,80,87,96],"(the":[10],"gradient":[11],"of":[12,15,26,39,47,94,117,149],"log-density)":[14],"probability":[17],"distribution":[18],"from":[19,102],"samples.":[20],"It":[21],"has":[22,132],"found":[23],"number":[25,148],"applications,":[27],"including":[28,106],"in":[29,60],"generative":[30],"modeling,":[31],"where":[32,63],"it":[33],"serves":[34],"as":[35],"key":[37,73],"component":[38],"state-of-the-art":[41],"diffusion":[42],"modeling":[43],"framework.":[44],"The":[45,129],"goal":[46],"this":[48],"work":[49],"to":[51,125,143],"provide":[52],"non-asymptotic":[53],"bounds":[54,108],"on":[55,91,135],"risk":[59],"setting":[62],"model":[66,81],"deep":[69],"neural":[70,118],"network.":[71],"Here":[72],"challenges":[74],"include":[75],"fact":[77],"that":[78,85],"vector-valued":[83],"and":[84,109],"loss":[89],"depends":[90],"Jacobian":[93],"model.":[97],"Our":[98],"integrates":[100],"results":[101,124],"empirical":[103],"process":[104],"theory,":[105],"classical":[107],"recently":[110],"introduced":[111],"techniques":[112],"bounding":[114],"covering":[115,123],"numbers":[116],"network":[119,137,141],"models,":[120],"with":[121,146],"novel":[122],"address":[126],"these":[127],"challenges.":[128],"resulting":[130],"bound":[131],"logarithmic":[133],"dependence":[134],"width,":[138],"allowing":[139],"size":[142],"grow":[144],"exponentially":[145],"training":[150],"samples":[151],"without":[152],"compromising":[153],"bound.":[155]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}