{"id":"https://openalex.org/W2785916643","doi":null,"title":"Variational Network Quantization","display_name":"Variational Network Quantization","publication_year":2018,"publication_date":"2018-02-15","ids":{"openalex":"https://openalex.org/W2785916643","mag":"2785916643"},"language":"en","primary_location":{"id":"mag:2785916643","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=ry-TW-WAb","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5112617537","display_name":"Jan Achterhold","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Achterhold","raw_affiliation_strings":["RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026633086","display_name":"Jan Mathias Koehler","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Mathias Koehler","raw_affiliation_strings":["Robert Bosch GmBH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch GmBH","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072895220","display_name":"Anke Schmeink","orcid":"https://orcid.org/0000-0002-9929-2925","observed_orcids":["https://orcid.org/0000-0002-9929-2925"]},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anke Schmeink","raw_affiliation_strings":["RWTH Aachen University"],"raw_orcid":"https://orcid.org/0000-0002-9929-2925","affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013602545","display_name":"Tim Genewein","orcid":"https://orcid.org/0000-0001-8039-4027","observed_orcids":["https://orcid.org/0000-0001-8039-4027"]},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Genewein","raw_affiliation_strings":["Robert Bosch (Germany), Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8039-4027","affiliations":[{"raw_affiliation_string":"Robert Bosch (Germany), Stuttgart, Germany","institution_ids":["https://openalex.org/I889804353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1495,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.94833801,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9980000257492065,"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":0.9980000257492065,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0005000000237487257,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.00019999999494757503,"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/neural-network-pruning","display_name":"neural network pruning","score":0.8479999899864197},{"id":"https://openalex.org/keywords/ternary-quantization","display_name":"ternary quantization","score":0.8899999856948853},{"id":"https://openalex.org/keywords/variational-bayesian-inference","display_name":"variational inference","score":0.9390000104904175},{"id":"https://openalex.org/keywords/weight-quantization","display_name":"weight quantization","score":0.6399999856948853},{"id":"https://openalex.org/keywords/lenet-5","display_name":"LeNet-5","score":0.6769999861717224},{"id":"https://openalex.org/keywords/densenet-121","display_name":"DenseNet121","score":0.9959999918937683}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.8174988031387329},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6846266984939575},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5452509522438049},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48226648569107056},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45579656958580017},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4544163644313812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4460766315460205},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3868306279182434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32607001066207886},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.12867847084999084}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2785916643","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=ry-TW-WAb","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W35527955","https://openalex.org/W45374770","https://openalex.org/W582134693","https://openalex.org/W1567512734","https://openalex.org/W1959608418","https://openalex.org/W1999974018","https://openalex.org/W2054658115","https://openalex.org/W2101460669","https://openalex.org/W2108677974","https://openalex.org/W2112796928","https://openalex.org/W2114766824","https://openalex.org/W2125389748","https://openalex.org/W2139701068","https://openalex.org/W2161758346","https://openalex.org/W2165082320","https://openalex.org/W2167433878","https://openalex.org/W2509836288","https://openalex.org/W2604319603","https://openalex.org/W2612445135","https://openalex.org/W2619890685","https://openalex.org/W2951595529","https://openalex.org/W2952746978","https://openalex.org/W2963071676","https://openalex.org/W2963446712","https://openalex.org/W2964299589","https://openalex.org/W3118608800","https://openalex.org/W3140968660"],"related_works":["https://openalex.org/W4229444149","https://openalex.org/W4417119466","https://openalex.org/W4226086854","https://openalex.org/W3004379541","https://openalex.org/W2884150179","https://openalex.org/W2799197246","https://openalex.org/W3001665736","https://openalex.org/W4327661596","https://openalex.org/W3179996328","https://openalex.org/W2735241311"],"abstract_inverted_index":{"In":[0],"this":[1,22,46],"paper,":[2],"the":[3],"preparation":[4],"of":[5,69],"a":[6,17,24,30,40],"neural":[7],"network":[8],"for":[9,45,90],"pruning":[10,73],"and":[11,39,96],"few-bit":[12],"quantization":[13,62,92],"is":[14,37,48],"formulated":[15],"as":[16],"variational":[18],"inference":[19],"problem.":[20],"To":[21],"end":[23],"quantizing":[25],"prior":[26,47],"that":[27],"leads":[28],"to":[29,66,77],"multi-modal,":[31],"sparse":[32],"posterior":[33],"distribution":[34],"over":[35],"weights":[36,56,76],"introduced":[38],"differentiable":[41],"Kullback-Leibler":[42],"divergence":[43],"approximation":[44],"derived.":[49],"After":[50],"training":[51],"with":[52,64],"Variational":[53],"Network":[54],"Quantization,":[55],"can":[57],"be":[58],"replaced":[59],"by":[60,74],"deterministic":[61],"values":[63],"small":[65],"negligible":[67],"loss":[68],"task":[70],"accuracy":[71],"(including":[72],"setting":[75],"0).":[78],"The":[79],"method":[80],"does":[81],"not":[82],"require":[83],"fine-tuning":[84],"after":[85],"quantization.":[86],"Results":[87],"are":[88],"shown":[89],"ternary":[91],"on":[93],"LeNet-5":[94],"(MNIST)":[95],"DenseNet-121":[97],"(CIFAR-10).":[98]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":7}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2018-02-23T00:00:00"}