{"id":"https://openalex.org/W4392903603","doi":"https://doi.org/10.1109/icassp48485.2024.10447855","title":"Learning Dynamics of Low-Precision Clipped SGD with Momentum","display_name":"Learning Dynamics of Low-Precision Clipped SGD with Momentum","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903603","doi":"https://doi.org/10.1109/icassp48485.2024.10447855"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04760253/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015999129","display_name":"Roula Nassif","orcid":"https://orcid.org/0000-0001-9663-8559"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Roula Nassif","raw_affiliation_strings":["Université Côte d'Azur,I3S Laboratory, CNRS,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Côte d'Azur,I3S Laboratory, CNRS,France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077268766","display_name":"Soummya Kar","orcid":"https://orcid.org/0000-0002-8060-5581"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soummya Kar","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","CMU - Carnegie Mellon University [Pittsburgh] (5000 Forbes Ave, Pittsburgh, PA 15213 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"CMU - Carnegie Mellon University [Pittsburgh] (5000 Forbes Ave, Pittsburgh, PA 15213 - United States)","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083805703","display_name":"Stefan Vlaski","orcid":"https://orcid.org/0000-0002-0616-3076"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefan Vlaski","raw_affiliation_strings":["Imperial College London,UK","Imperial College London (South Kensington Campus, London SW7 2AZ - United Kingdom)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London (South Kensington Campus, London SW7 2AZ - United Kingdom)","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3543,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4757334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6075","last_page":"6079"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9980999827384949,"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":0.9980999827384949,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.7448742389678955},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7390012145042419},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.6053165793418884},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.5653833150863647},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5427418947219849},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5028192400932312},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5002765655517578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4842042922973633},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.43918377161026},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3772914707660675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22351589798927307},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20379942655563354}],"concepts":[{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.7448742389678955},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7390012145042419},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.6053165793418884},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.5653833150863647},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5427418947219849},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5028192400932312},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5002765655517578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4842042922973633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43918377161026},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3772914707660675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22351589798927307},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20379942655563354},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04760253v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04760253","pdf_url":"https://hal.science/hal-04760253/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, South Korea. pp.6075-6079, ⟨10.1109/ICASSP48485.2024.10447855⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04760253v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04760253","pdf_url":"https://hal.science/hal-04760253/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, South Korea. pp.6075-6079, ⟨10.1109/ICASSP48485.2024.10447855⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G7104411396","display_name":"Communication-efficient decentralized, adaptive and reliable optimization over multitask graphs","funder_award_id":"ANR-22-CE23-0015","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392903603.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W809736386","https://openalex.org/W1972711404","https://openalex.org/W1988720110","https://openalex.org/W2595897327","https://openalex.org/W2647836899","https://openalex.org/W2791110811","https://openalex.org/W2962795635","https://openalex.org/W3035232708","https://openalex.org/W3088745370","https://openalex.org/W3133262835","https://openalex.org/W3186261059","https://openalex.org/W4205555171","https://openalex.org/W4205987271","https://openalex.org/W4224932487","https://openalex.org/W4299689471","https://openalex.org/W4378764988","https://openalex.org/W4381199009","https://openalex.org/W6638783484","https://openalex.org/W6739513683","https://openalex.org/W6746200960","https://openalex.org/W6751528251","https://openalex.org/W6758557334","https://openalex.org/W6762930437","https://openalex.org/W6766923583","https://openalex.org/W6772129282","https://openalex.org/W6778239092","https://openalex.org/W6780688020","https://openalex.org/W6839879718","https://openalex.org/W6843823278"],"related_works":["https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W4231621013","https://openalex.org/W4362706668","https://openalex.org/W3007093918","https://openalex.org/W3008318776","https://openalex.org/W1977633006","https://openalex.org/W2041416246"],"abstract_inverted_index":{"In":[0,20],"this":[1],"work,":[2],"we":[3],"present":[4],"and":[5,30,41,60,102],"study":[6],"a":[7],"low-precision":[8,76],"variant":[9,80],"of":[10,56,65,81,105],"the":[11,36,48,53,57,63,66,75,78,82,93,99,103,106],"stochastic":[12,67],"gradient":[13,68],"descent":[14],"(SGD)":[15],"algorithm":[16,85],"with":[17,26,86],"adaptive":[18],"quantization.":[19],"particular,":[21],"fixed-rate":[22,58],"probabilistic":[23],"uniform":[24],"quantizers":[25],"varying":[27],"quantization":[28],"steps":[29],"mid-values":[31],"are":[32,43],"used":[33,44],"to":[34,45,61,90],"compress":[35],"parameter":[37],"vectors.":[38],"Gradient":[39],"clipping":[40],"momentum":[42,87],"guarantee":[46],"that":[47],"quantizer":[49,59],"inputs":[50],"fall":[51],"within":[52],"representable":[54],"region":[55],"reduce":[62],"impact":[64],"noise,":[69],"respectively.":[70],"We":[71],"show":[72],"that,":[73],"despite":[74],"representation,":[77],"quantized":[79],"clipped":[83],"SGD":[84],"is":[88],"able":[89],"converge":[91],"in":[92],"mean-square-error":[94],"sense.":[95],"Simulation":[96],"results":[97],"illustrate":[98],"theoretical":[100],"findings":[101],"effectiveness":[104],"proposed":[107],"approach.":[108]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}