{"id":"https://openalex.org/W7222223671","doi":"https://doi.org/10.48550/arxiv.2610.20075","title":"A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization","display_name":"A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization","publication_year":2026,"publication_date":"2026-10-14","ids":{"openalex":"https://openalex.org/W7222223671","doi":"https://doi.org/10.48550/arxiv.2610.20075"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.20075","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.20075","pdf_url":"https://arxiv.org/pdf/2610.20075","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/2610.20075","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016789295","display_name":"Ekkehard Schnoor","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Schnoor, Ekkehard","raw_affiliation_strings":["Aalto University Espoo , Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University Espoo , Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008573276","display_name":"Malik Tiomoko","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tiomoko, Malik","raw_affiliation_strings":["Aalto University Espoo , Finland","Huawei Noah's Ark Lab Paris , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University Espoo , Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab Paris , France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006624933","display_name":"Alexander Jung","orcid":"https://orcid.org/0000-0001-7538-0990","observed_orcids":["https://orcid.org/0000-0001-7538-0990"]},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jung, Alexander","raw_affiliation_strings":["Aalto University Espoo , Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University Espoo , Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9927081"],"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9419000148773193,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9419000148773193,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.026200000196695328,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.009399999864399433,"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/federated-learning","display_name":"federated learning","score":0.9950000047683716},{"id":"https://openalex.org/keywords/least-squares-regression","display_name":"least squares regression","score":0.8379999995231628},{"id":"https://openalex.org/keywords/random-matrix-theory","display_name":"random matrix theory","score":0.9359999895095825},{"id":"https://openalex.org/keywords/decentralized-networks","display_name":"decentralized networks","score":0.7680000066757202},{"id":"https://openalex.org/keywords/non-iid-data","display_name":"non-IID data","score":0.7229999899864197},{"id":"https://openalex.org/keywords/regularization","display_name":"regularization","score":0.4000000059604645},{"id":"https://openalex.org/keywords/local-adaptation","display_name":"local adaptation","score":0.42800000309944153},{"id":"https://openalex.org/keywords/gaussian-mixture-distribution","display_name":"Gaussian mixture distribution","score":0.6110000014305115},{"id":"https://openalex.org/keywords/asymptotic-performance","display_name":"asymptotic performance","score":0.6869999766349792}],"concepts":[{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.6506999731063843},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.6478999853134155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5781999826431274},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5565000176429749},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45750001072883606},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C107321475","wikidata":"https://www.wikidata.org/wiki/Q5374254","display_name":"Empirical risk minimization","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3727000057697296},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.36340001225471497},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3495999872684479},{"id":"https://openalex.org/C64812099","wikidata":"https://www.wikidata.org/wiki/Q176604","display_name":"Random matrix","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.20075","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.20075","pdf_url":"https://arxiv.org/pdf/2610.20075","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.20075","doi":"https://doi.org/10.48550/arxiv.2610.20075","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.20075","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.20075","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.20075","pdf_url":"https://arxiv.org/pdf/2610.20075","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222223671.pdf","grobid_xml":"https://content.openalex.org/works/W7222223671.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2750384547","https://openalex.org/W2924303691","https://openalex.org/W3005776401","https://openalex.org/W3007548213","https://openalex.org/W3109662046","https://openalex.org/W4417114107"],"related_works":["https://openalex.org/W4387872106","https://openalex.org/W4404609484","https://openalex.org/W7213424813","https://openalex.org/W7213600521","https://openalex.org/W4385968143","https://openalex.org/W7117969563","https://openalex.org/W3194748595","https://openalex.org/W2972497108","https://openalex.org/W3176457956","https://openalex.org/W3208210999"],"abstract_inverted_index":{"Federated":[0],"learning":[1],"over":[2],"decentralized":[3],"networks":[4],"inherently":[5],"trades":[6],"off":[7],"the":[8,17,54,74,91],"suppression":[9],"of":[10,34,53],"local":[11,99],"finite-sample":[12],"noise":[13],"through":[14],"collaboration":[15,20],"against":[16,101],"bias":[18],"that":[19,50],"introduces":[21],"between":[22],"heterogeneous":[23],"nodes.":[24],"We":[25,68],"study":[26],"this":[27],"tension":[28],"by":[29,108],"performing":[30],"a":[31,87],"large-dimensional":[32],"analysis":[33],"Generalized":[35],"Total":[36],"Variation":[37],"Minimization":[38],"with":[39],"least-squares":[40],"models.":[41],"Using":[42],"tools":[43],"from":[44],"random":[45],"matrix":[46],"theory,":[47],"we":[48],"show":[49],"Lipschitz":[51],"observations":[52],"global":[55],"GTVMin":[56],"solution":[57],"concentrate":[58],"in":[59],"large":[60],"dimensions,":[61],"universally":[62],"for":[63,73],"any":[64],"underlying":[65],"network":[66],"structure.":[67],"provide":[69],"exact":[70],"analytic":[71],"expressions":[72,94],"asymptotically":[75],"precise":[76],"performance":[77],"under":[78],"both":[79],"i.i.d.":[80],"and":[81,112],"non-i.i.d.":[82],"Gaussian":[83],"mixture":[84],"distributions":[85],"on":[86,110],"fixed":[88],"network.":[89],"For":[90],"latter,":[92],"these":[93],"quantify":[95],"how":[96],"regularization":[97],"balances":[98],"adaptation":[100],"collaboration.":[102],"Our":[103],"theoretical":[104],"results":[105],"are":[106],"confirmed":[107],"experiments":[109],"synthetic":[111],"real-world":[113],"data.":[114]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-16T00:00:00"}