{"id":"https://openalex.org/W4408062286","doi":"https://doi.org/10.5220/0013382400003890","title":"When Are 1.58 Bits Enough? A Bottom-up Exploration of Quantization-Aware Training with Ternary Weights","display_name":"When Are 1.58 Bits Enough? A Bottom-up Exploration of Quantization-Aware Training with Ternary Weights","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408062286","doi":"https://doi.org/10.5220/0013382400003890"},"language":"en","primary_location":{"id":"doi:10.5220/0013382400003890","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013382400003890","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0013382400003890","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072161944","display_name":"Jacob Woge Nielsen","orcid":"https://orcid.org/0000-0002-5466-7869"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jacob Nielsen","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114656612","display_name":"Lukas Galke","orcid":null},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Lukas Galke","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104621238","display_name":"Peter Schneider-Kamp","orcid":null},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Peter Schneider-Kamp","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177969490"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1440","last_page":"1449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9333000183105469,"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/T10320","display_name":"Neural Networks and Applications","score":0.9333000183105469,"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/computer-science","display_name":"Computer science","score":0.6847212314605713},{"id":"https://openalex.org/keywords/ternary-operation","display_name":"Ternary operation","score":0.6516512632369995},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6261797547340393},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4595524072647095},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19134017825126648}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6847212314605713},{"id":"https://openalex.org/C64452783","wikidata":"https://www.wikidata.org/wiki/Q1524945","display_name":"Ternary operation","level":2,"score":0.6516512632369995},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6261797547340393},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4595524072647095},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19134017825126648},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0013382400003890","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013382400003890","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:sdu.dk:openaire/f3201945-87ef-4a38-a8ac-9791df95fb27","is_oa":false,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/f3201945-87ef-4a38-a8ac-9791df95fb27","pdf_url":null,"source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.5220/0013382400003890","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013382400003890","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"Contemporary":[0],"machine":[1],"learning":[2],"models,":[3,7,111],"such":[4,57],"as":[5],"language":[6,38,60,88,126],"are":[8],"powerful,":[9],"but":[10],"come":[11],"with":[12,25,73,108],"immense":[13],"resource":[14],"requirements":[15],"both":[16],"at":[17,129],"training":[18,51,54,84,104],"and":[19,40,76,91],"inference":[20],"time.":[21],"Quantization":[22],"aware":[23],"pre-training":[24],"ternary":[26],"weights":[27],"(1.58":[28],"bits":[29],"per":[30],"weight)":[31],"has":[32],"shown":[33],"promising":[34],"results":[35,95,123],"in":[36,65,85,98],"decoder-only":[37,59],"models":[39,127],"facilitates":[41],"memoryefficient":[42],"inference.":[43],"However,":[44],"little":[45],"is":[46,105],"known":[47],"about":[48],"how":[49],"quantization-aware":[50,70,136],"influences":[52],"the":[53],"dynamics":[55],"beyond":[56],"Transformer-based":[58],"models.":[61,93,121],"Here,":[62],"we":[63,81,113],"engage":[64],"a":[66,130],"bottom-up":[67],"exploration":[68],"of":[69,100],"training,":[71],"starting":[72],"multi-layer":[74],"perceptrons":[75],"graph":[77],"neural":[78],"networks.":[79],"Then,":[80],"explore":[82],"1.58-bit":[83,103,119],"other":[86],"transformer-based":[87],"models:":[89],"encoder-only":[90],"encoderdecoder":[92],"Our":[94,122],"show":[96],"that":[97],"all":[99],"these":[101],"settings,":[102],"on":[106,124],"par":[107],"standard":[109],"32/16-bit":[110],"yet":[112],"also":[114],"identify":[115],"challenges":[116],"specific":[117],"to":[118],"encoder-decoder":[120],"decoderonly":[125],"hint":[128],"possible":[131],"regularization":[132],"effect":[133],"introduced":[134],"by":[135],"training.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}