{"id":"https://openalex.org/W7161269321","doi":"https://doi.org/10.48550/arxiv.2605.14860","title":"A Non-Monotone Preconditioned Trust-Region Method for Neural Network Training","display_name":"A Non-Monotone Preconditioned Trust-Region Method for Neural Network Training","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161269321","doi":"https://doi.org/10.48550/arxiv.2605.14860"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2605.14860","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.14860","pdf_url":"https://arxiv.org/pdf/2605.14860","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":"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/2605.14860","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107289610","display_name":"Andrea Angino","orcid":"https://orcid.org/0009-0000-8525-375X","observed_orcids":["https://orcid.org/0009-0000-8525-375X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Angino, Andrea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120846171","display_name":"Bindi \u00c7apriqi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u00c7apriqi, Bindi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120846172","display_name":"Shega Likaj","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Likaj, Shega","raw_affiliation_strings":["Universit\u00e0 della Svizzera italiana ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 della Svizzera italiana ;","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085559236","display_name":"Ken Trotti","orcid":"https://orcid.org/0000-0002-5496-9445","observed_orcids":["https://orcid.org/0000-0002-5496-9445"]},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Trotti, Ken","raw_affiliation_strings":["King Abdullah University of Science and Technology ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology ;","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136197507","display_name":"Rolf Krause","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Krause, Rolf","raw_affiliation_strings":["Universit\u00e0 della Svizzera italiana ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 della Svizzera italiana ;","institution_ids":["https://openalex.org/I57201433"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.8227999806404114,"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":0.8227999806404114,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.07180000096559525,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.05869999900460243,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/trust-region-method","display_name":"trust region method","score":0.7120000123977661},{"id":"https://openalex.org/keywords/neural-network-training","display_name":"neural network training","score":0.7059999704360962},{"id":"https://openalex.org/keywords/domain-decomposition","display_name":"domain decomposition","score":0.847000002861023},{"id":"https://openalex.org/keywords/additive-schwarz-preconditioner","display_name":"additive Schwarz preconditioner","score":0.8790000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7039999961853027},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6996999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5342000126838684},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5245000123977661},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.512499988079071},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39629998803138733},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32499998807907104},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2556999921798706},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2605.14860","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.14860","pdf_url":"https://arxiv.org/pdf/2605.14860","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2605.14860","doi":"https://doi.org/10.48550/arxiv.2605.14860","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14860","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:2605.14860","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.14860","pdf_url":"https://arxiv.org/pdf/2605.14860","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1387836630","display_name":"Numerical Methods for Efficient Acoustic Metamaterial Design","funder_award_id":"224943","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G3777672830","display_name":"ML2 - Multilevel and Domain Decomposition Methods for Machine Learning","funder_award_id":"197041","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7161269321.pdf","grobid_xml":"https://content.openalex.org/works/W7161269321.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4311653698","https://openalex.org/W4417467485"],"related_works":["https://openalex.org/W4409704506","https://openalex.org/W4390136752","https://openalex.org/W4417467485","https://openalex.org/W4409777889","https://openalex.org/W3083868165","https://openalex.org/W4399794734","https://openalex.org/W2785602206","https://openalex.org/W4400874554","https://openalex.org/W4415913722","https://openalex.org/W4394714806"],"abstract_inverted_index":{"Training":[0],"deep":[1],"neural":[2],"networks":[3],"at":[4],"scale":[5],"can":[6],"benefit":[7],"from":[8],"domain":[9],"decomposition,":[10],"where":[11],"the":[12,30],"network":[13],"is":[14],"split":[15],"into":[16],"subdomains":[17],"trained":[18],"in":[19,93],"parallel":[20,49],"and":[21,84],"coupled":[22],"by":[23,82],"a":[24,38,42],"global":[25,53],"trust-region":[26],"mechanism.":[27],"Building":[28],"on":[29],"Additively":[31],"Preconditioned":[32],"Trust-Region":[33],"Strategy":[34],"(APTS),":[35],"we":[36],"propose":[37],"non-monotone":[39,73],"variant":[40],"with":[41,52],"nonlinear":[43],"additive":[44],"Schwarz":[45],"preconditioner":[46],"that":[47],"combines":[48],"subdomain":[50],"corrections":[51],"coarse-space":[54],"directions.":[55],"A":[56],"windowed":[57],"acceptance":[58],"criterion":[59],"allows":[60],"controlled":[61],"objective":[62],"increases,":[63],"avoiding":[64],"needless":[65],"rejection":[66],"of":[67,91],"effective":[68],"coarse":[69],"steps.":[70],"The":[71],"resulting":[72],"APTS":[74],"(NAPTS)":[75],"preserves":[76],"accuracy":[77],"while":[78],"reducing":[79],"CPU":[80],"time":[81],"30\\%":[83],"cutting":[85],"rejected":[86],"steps":[87],"to":[88],"one":[89],"third":[90],"those":[92],"APTS.":[94]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-05-16T00:00:00"}