{"id":"https://openalex.org/W4389166756","doi":"https://doi.org/10.1109/iccad57390.2023.10323830","title":"Improving Realistic Worst-Case Performance of NVCiM DNN Accelerators Through Training with Right-Censored Gaussian Noise","display_name":"Improving Realistic Worst-Case Performance of NVCiM DNN Accelerators Through Training with Right-Censored Gaussian Noise","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4389166756","doi":"https://doi.org/10.1109/iccad57390.2023.10323830"},"language":"en","primary_location":{"id":"doi:10.1109/iccad57390.2023.10323830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad57390.2023.10323830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD)","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/A5059093077","display_name":"Zheyu Yan","orcid":"https://orcid.org/0000-0003-1830-606X"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zheyu Yan","raw_affiliation_strings":["Uuiversity of Notre Dame"],"affiliations":[{"raw_affiliation_string":"Uuiversity of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102727136","display_name":"Yifan Qin","orcid":"https://orcid.org/0000-0001-6559-9913"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Qin","raw_affiliation_strings":["Uuiversity of Notre Dame"],"affiliations":[{"raw_affiliation_string":"Uuiversity of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103129518","display_name":"Wujie Wen","orcid":"https://orcid.org/0000-0003-3440-1905"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wujie Wen","raw_affiliation_strings":["North Carolina State University"],"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600905","display_name":"Xiaobo Sharon Hu","orcid":"https://orcid.org/0000-0002-6636-9738"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaobo Sharon Hu","raw_affiliation_strings":["Uuiversity of Notre Dame"],"affiliations":[{"raw_affiliation_string":"Uuiversity of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000141831","display_name":"Yiyu Shi","orcid":"https://orcid.org/0000-0002-6788-9823"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiyu Shi","raw_affiliation_strings":["Uuiversity of Notre Dame"],"affiliations":[{"raw_affiliation_string":"Uuiversity of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059093077"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":1.7194,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87043885,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976999759674072,"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/gaussian-noise","display_name":"Gaussian noise","score":0.7162823677062988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6923952102661133},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6660453081130981},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6629688739776611},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6584254503250122},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5672271251678467},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.5247319340705872},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5104736089706421},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5032240748405457},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48841995000839233},{"id":"https://openalex.org/keywords/impulse-noise","display_name":"Impulse noise","score":0.43589308857917786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4235972762107849},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35763633251190186},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3474158048629761},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33576250076293945},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10082840919494629}],"concepts":[{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.7162823677062988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923952102661133},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6660453081130981},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6629688739776611},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6584254503250122},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5672271251678467},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.5247319340705872},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5104736089706421},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5032240748405457},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48841995000839233},{"id":"https://openalex.org/C127372701","wikidata":"https://www.wikidata.org/wiki/Q16979398","display_name":"Impulse noise","level":3,"score":0.43589308857917786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4235972762107849},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35763633251190186},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3474158048629761},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33576250076293945},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10082840919494629},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad57390.2023.10323830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad57390.2023.10323830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2442974303","https://openalex.org/W2518281301","https://openalex.org/W2795127895","https://openalex.org/W3005619596","https://openalex.org/W3013462594","https://openalex.org/W3022053993","https://openalex.org/W3085709740","https://openalex.org/W3092873005","https://openalex.org/W3109808781","https://openalex.org/W3118608800","https://openalex.org/W3201655817","https://openalex.org/W3211724015","https://openalex.org/W3212633509","https://openalex.org/W3213069285","https://openalex.org/W3214603841","https://openalex.org/W4213079971","https://openalex.org/W4226216109","https://openalex.org/W4245994158","https://openalex.org/W4281289797","https://openalex.org/W4292779060","https://openalex.org/W4293024037","https://openalex.org/W4312076514","https://openalex.org/W4379113625","https://openalex.org/W4386767094","https://openalex.org/W6637373629","https://openalex.org/W6762631276","https://openalex.org/W6771019708","https://openalex.org/W6778883912","https://openalex.org/W6784426856","https://openalex.org/W6790978476","https://openalex.org/W6798528302","https://openalex.org/W6803554409","https://openalex.org/W6929299282"],"related_works":["https://openalex.org/W2159720070","https://openalex.org/W2463830379","https://openalex.org/W1991133639","https://openalex.org/W2157134024","https://openalex.org/W2165264176","https://openalex.org/W2290527899","https://openalex.org/W2064270814","https://openalex.org/W2286538174","https://openalex.org/W2016732018","https://openalex.org/W2985488186"],"abstract_inverted_index":{"Compute-in-Memory":[0],"(CiM),":[1],"built":[2],"upon":[3],"non-volatile":[4],"memory":[5],"(NVM)":[6],"devices,":[7],"is":[8,34,68,88,139],"promising":[9],"for":[10,117,150,177],"accelerating":[11],"deep":[12],"neural":[13],"networks":[14],"(DNNs)":[15],"owing":[16],"to":[17,45,51,105,145,172,191,198,203],"its":[18,55],"in-situ":[19],"data":[20],"processing":[21],"capability":[22],"and":[23,63],"superior":[24],"energy":[25],"efficiency.":[26],"To":[27],"battle":[28],"device":[29,211],"variations,":[30],"noise":[31,42,102,138,159,182],"injection":[32],"training":[33,44,104,185],"commonly":[35],"used,":[36],"which":[37],"perturbs":[38],"weights":[39],"with":[40],"Gaussian":[41,78,101,137,158,181],"during":[43,183],"make":[46],"the":[47,71,97,107,118,127,130,141,153,162,174,184,199,208],"model":[48],"more":[49],"robust":[50],"weight":[52],"variations.":[53,212],"Despite":[54],"prevalence,":[56],"however,":[57],"existing":[58],"successes":[59],"are":[60],"mostly":[61],"empirical,":[62],"very":[64],"little":[65],"theoretical":[66,124],"support":[67],"available.":[69],"Even":[70],"most":[72],"fundamental":[73],"questions":[74],"such":[75],"as":[76],"why":[77],"but":[79],"not":[80,89,140],"other":[81],"types":[82],"of":[83,99,126,129,164,210],"noises":[84],"should":[85],"be":[86],"used":[87],"answered.":[90],"In":[91],"this":[92,179],"work,":[93],"through":[94],"formally":[95],"analyzing":[96],"effect":[98],"injecting":[100,178],"in":[103,152,195],"improve":[106],"k-th":[108],"percentile":[109],"performance":[110,115],"(KPP),":[111],"a":[112,123,156,192],"realistic":[113],"worst-case":[114],"metric,":[116],"first":[119],"time":[120],"we":[121],"provide":[122],"justification":[125],"effectiveness":[128],"approach.":[131],"We":[132,166],"further":[133,167],"show":[134],"that":[135],"surprisingly":[136],"best":[142],"option,":[143],"contrary":[144],"what":[146],"has":[147],"been":[148],"taken":[149],"granted":[151],"literature.":[154],"Instead,":[155],"right-censored":[157,180],"significantly":[160],"improves":[161],"KPP":[163,196],"DNNs.":[165],"propose":[168],"an":[169],"automated":[170],"method":[171,188],"determine":[173],"optimal":[175],"hyperparameters":[176],"process.":[186],"Our":[187],"achieves":[189],"up":[190],"26%":[193],"improvement":[194],"compared":[197],"state-of-the-art":[200],"methods":[201],"employed":[202],"enhance":[204],"DNN":[205],"robustness":[206],"under":[207],"impact":[209]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}