{"id":"https://openalex.org/W7216006538","doi":"https://doi.org/10.48550/arxiv.2610.00738","title":"Q-MINO: A Minimal-Norm Method for Quantization-Aware Training","display_name":"Q-MINO: A Minimal-Norm Method for Quantization-Aware Training","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7216006538","doi":"https://doi.org/10.48550/arxiv.2610.00738"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.00738","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00738","pdf_url":"https://arxiv.org/pdf/2610.00738","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.00738","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135980310","display_name":"Don Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Li, Don","raw_affiliation_strings":["Department of Mathematics & Statistics Portland State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics & Statistics Portland State University","institution_ids":["https://openalex.org/I126345244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5135980310"],"corresponding_institution_ids":["https://openalex.org/I126345244"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.8833000063896179,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.8833000063896179,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09470000118017197,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0034000000450760126,"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/quantization-aware-training","display_name":"quantization-aware training","score":0.9990000128746033},{"id":"https://openalex.org/keywords/straight-through-estimator","display_name":"straight-through estimator","score":0.8019999861717224},{"id":"https://openalex.org/keywords/alignment-constraints","display_name":"alignment constraints","score":0.6940000057220459},{"id":"https://openalex.org/keywords/frank-wolfe-algorithm","display_name":"Frank-Wolfe algorithm","score":0.7879999876022339},{"id":"https://openalex.org/keywords/low-bit-quantization","display_name":"low-bit quantization","score":0.7319999933242798}],"concepts":[{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6003999710083008},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5758000016212463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5681999921798706},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5637000203132629},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.554099977016449},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.41499999165534973},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39329999685287476},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3490000069141388},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2718000113964081}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.00738","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00738","pdf_url":"https://arxiv.org/pdf/2610.00738","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.00738","doi":"https://doi.org/10.48550/arxiv.2610.00738","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.00738","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.00738","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00738","pdf_url":"https://arxiv.org/pdf/2610.00738","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7216006538.pdf","grobid_xml":"https://content.openalex.org/works/W7216006538.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2242818861","https://openalex.org/W2948223045","https://openalex.org/W3001279689","https://openalex.org/W3170437634","https://openalex.org/W4225857786","https://openalex.org/W4287254789","https://openalex.org/W4404390875","https://openalex.org/W4415798985","https://openalex.org/W4417307874"],"related_works":["https://openalex.org/W7125913284","https://openalex.org/W7162471721","https://openalex.org/W4417115583","https://openalex.org/W4311427561","https://openalex.org/W3097481549","https://openalex.org/W7154099105","https://openalex.org/W4416167030","https://openalex.org/W4414562357","https://openalex.org/W4386066352","https://openalex.org/W4417100690"],"abstract_inverted_index":{"The":[0],"Straight-Through":[1],"Estimator":[2],"(STE)":[3],"is":[4],"a":[5,44,75,80,86],"widely":[6],"used":[7],"heuristic":[8],"for":[9],"Quantization-Aware":[10,40],"Training":[11],"(QAT),":[12],"but":[13],"its":[14],"surrogate":[15],"gradients":[16],"can":[17],"exhibit":[18],"substantial":[19],"mismatch":[20],"with":[21,79,105],"the":[22,39,70],"underlying":[23],"quantized":[24],"objective,":[25],"leading":[26],"to":[27,58],"noisy":[28],"updates":[29],"and":[30,54],"parameter":[31],"oscillations,":[32],"particularly":[33],"in":[34],"ultra-low-bit":[35],"regimes.":[36],"We":[37],"propose":[38],"Minimal-Norm":[41],"Optimizer":[42],"(Q-MINO),":[43],"temporal":[45],"bundle":[46],"method":[47],"that":[48,94],"combines":[49],"gradient":[50],"consensus,":[51],"state-drift":[52],"regularization,":[53],"an":[55],"alignment":[56],"constraint":[57],"construct":[59],"stabilized,":[60],"minimum-norm":[61],"update":[62],"directions":[63],"from":[64],"recent":[65],"optimization":[66],"states.":[67],"Q-MINO":[68,95,106],"solves":[69],"resulting":[71],"constrained":[72],"subproblem":[73],"using":[74],"warm-started":[76],"Frank--Wolfe":[77],"procedure":[78],"feasible":[81],"fallback":[82],"initialization.":[83],"Theoretically,":[84],"via":[85],"stochastic":[87],"Lyapunov":[88],"Kurdyka--\u0141ojasiewicz":[89],"(KL)":[90],"framework,":[91],"we":[92,101],"show":[93],"achieves":[96],"asymptotic":[97],"neighborhood":[98],"convergence.":[99],"Moreover,":[100],"detail":[102],"numerical":[103],"experiments":[104],"at":[107],"various":[108],"quantizations.":[109]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}