{"id":"https://openalex.org/W4416429975","doi":"https://doi.org/10.1109/iccad66269.2025.11240930","title":"BARQ: Boundary-Aware Regularized Training for Accurate Inference on Computing-in-Memory Accelerators with Low-Precision A/D Conversion","display_name":"BARQ: Boundary-Aware Regularized Training for Accurate Inference on Computing-in-Memory Accelerators with Low-Precision A/D Conversion","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W4416429975","doi":"https://doi.org/10.1109/iccad66269.2025.11240930"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11240930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5009420055","display_name":"Tianxing Ren","orcid":"https://orcid.org/0009-0004-6461-1692"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tingrui Ren","raw_affiliation_strings":["Beihang University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071375151","display_name":"Wang Bi","orcid":"https://orcid.org/0000-0002-3591-4764"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bi Wang","raw_affiliation_strings":["Beihang University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100712623","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0002-0061-5502"},"institutions":[{"id":"https://openalex.org/I4210089056","display_name":"Beijing Microelectronics Technology Institute","ror":"https://ror.org/007y7ej30","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210089056"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["Beijing Microelectronics Technology Institute,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Microelectronics Technology Institute,Beijing,China","institution_ids":["https://openalex.org/I4210089056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030647669","display_name":"Yuanfu Zhao","orcid":"https://orcid.org/0000-0002-6786-6293"},"institutions":[{"id":"https://openalex.org/I4210089056","display_name":"Beijing Microelectronics Technology Institute","ror":"https://ror.org/007y7ej30","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210089056"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanfu Zhao","raw_affiliation_strings":["Beijing Microelectronics Technology Institute,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Microelectronics Technology Institute,Beijing,China","institution_ids":["https://openalex.org/I4210089056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009420055"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38691715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.4771000146865845,"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":0.4771000146865845,"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":0.2303999960422516,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.06340000033378601,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7764999866485596},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7283999919891357},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5787000060081482},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5638999938964844},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46619999408721924},{"id":"https://openalex.org/keywords/converters","display_name":"Converters","score":0.3903000056743622},{"id":"https://openalex.org/keywords/crossbar-switch","display_name":"Crossbar switch","score":0.3880000114440918},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7764999866485596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7321000099182129},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7283999919891357},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5638999938964844},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41679999232292175},{"id":"https://openalex.org/C2778422915","wikidata":"https://www.wikidata.org/wiki/Q10302051","display_name":"Converters","level":3,"score":0.3903000056743622},{"id":"https://openalex.org/C29984679","wikidata":"https://www.wikidata.org/wiki/Q1929149","display_name":"Crossbar switch","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3255999982357025},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C134146338","wikidata":"https://www.wikidata.org/wiki/Q1815901","display_name":"Electronic circuit","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1978259121","https://openalex.org/W2121927366","https://openalex.org/W2194775991","https://openalex.org/W2476548250","https://openalex.org/W2796472956","https://openalex.org/W2921351161","https://openalex.org/W2945592020","https://openalex.org/W3042468132","https://openalex.org/W3092032880","https://openalex.org/W3112740243","https://openalex.org/W3120770213","https://openalex.org/W3134195144","https://openalex.org/W3189489583","https://openalex.org/W3212727748","https://openalex.org/W4200001938","https://openalex.org/W4210261411","https://openalex.org/W4213436331","https://openalex.org/W4243519499","https://openalex.org/W4280533641","https://openalex.org/W4316661092","https://openalex.org/W4383337768","https://openalex.org/W4385255585","https://openalex.org/W4390872528","https://openalex.org/W4403677826","https://openalex.org/W4405598511"],"related_works":[],"abstract_inverted_index":{"Computing-in-Memory":[0],"(CIM)":[1],"with":[2,76,145],"ReRAM":[3],"crossbar":[4,38],"arrays":[5],"accelerates":[6],"Deep":[7],"Neural":[8],"Network":[9],"(DNN)":[10],"computations":[11],"by":[12,149,158,166],"executing":[13],"operations":[14],"directly":[15],"within":[16],"memory,":[17],"which":[18,114],"reduces":[19,155],"both":[20],"data":[21],"movement":[22],"and":[23,46,97,119,122,131,162],"energy":[24,156],"consumption.":[25],"Recent":[26],"studies":[27],"show":[28,134],"that":[29,57,135],"lowering":[30],"the":[31,50,128],"precision":[32],"of":[33,52,141],"Analog-to-Digital":[34],"Converters":[35],"(ADC)":[36],"in":[37,73],"peripheral":[39],"circuits":[40],"can":[41],"significantly":[42],"reduce":[43],"system":[44],"area":[45],"power":[47],"overheads":[48],"at":[49],"risk":[51],"increasing":[53],"quantization-induced":[54],"numerical":[55],"errors":[56,96],"degrade":[58],"inference":[59],"accuracy.":[60],"This":[61],"paper":[62],"proposes":[63],"a":[64,105],"Boundary-Aware":[65],"Regularized":[66],"Quantization":[67],"(BARQ)":[68],"technique":[69],"to":[70,85,160,169],"maintain":[71],"accuracy":[72,139],"CIM":[74],"accelerators":[75],"low-precision":[77],"ADCs.":[78,147],"BARQ":[79,136,153],"introduces":[80],"ADC":[81],"bit-width":[82],"boundary":[83],"constraints":[84],"regulate":[86],"model":[87],"weights":[88],"during":[89],"quantization-aware":[90],"training":[91],"(QAT),":[92],"mitigating":[93],"overflow-induced":[94],"clipping":[95],"enhancing":[98,150],"unstructured":[99],"weight":[100,107,151],"sparsity.":[101],"Additionally,":[102],"we":[103],"introduce":[104],"novel":[106],"initialization":[108],"strategy":[109],"based":[110],"on":[111,127],"Euclidean":[112],"projection,":[113],"minimizes":[115],"initial":[116],"quantization":[117,171],"error":[118],"facilitates":[120],"faster":[121],"more":[123],"stable":[124],"convergence.":[125],"Experiments":[126],"CIFAR-10,":[129],"CIFAR-100,":[130],"ImageNet":[132],"datasets":[133],"achieves":[137],"minimal":[138],"loss":[140],"only":[142],"0.59%":[143],"even":[144],"3-bit":[146],"Furthermore,":[148],"sparsity,":[152],"further":[154],"consumption":[157],"up":[159],"75%":[161],"improves":[163],"hardware":[164],"efficiency":[165],"3.79\u00d7":[167],"compared":[168],"conventional":[170],"methods.":[172]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-20T00:00:00"}