{"id":"https://openalex.org/W4390136752","doi":"https://doi.org/10.48550/arxiv.2312.13677","title":"Parallel Trust-Region Approaches in Neural Network Training: Beyond Traditional Methods","display_name":"Parallel Trust-Region Approaches in Neural Network Training: Beyond Traditional Methods","publication_year":2023,"publication_date":"2023-12-21","ids":{"openalex":"https://openalex.org/W4390136752","doi":"https://doi.org/10.48550/arxiv.2312.13677"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.13677","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.13677","pdf_url":"https://arxiv.org/pdf/2312.13677","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/2312.13677","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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/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":"Trotti, Ken","raw_affiliation_strings":["Universit\u00e0 della Svizzera italiana , Lugano , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 della Svizzera italiana , Lugano , Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093567658","display_name":"Samuel A. Cruz Alegr\u00eda","orcid":"https://orcid.org/0009-0004-5144-256X","observed_orcids":["https://orcid.org/0009-0004-5144-256X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alegr\u00eda, Samuel A. Cruz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080114950","display_name":"Alena Kopani\u010d\u00e1kov\u00e1","orcid":"https://orcid.org/0000-0001-8388-5518","observed_orcids":["https://orcid.org/0000-0001-8388-5518"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kopani\u010d\u00e1kov\u00e1, Alena","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052850078","display_name":"Rolf Krause","orcid":"https://orcid.org/0000-0001-5408-5271","observed_orcids":["https://orcid.org/0000-0001-5408-5271"]},"institutions":[{"id":"https://openalex.org/I4210134521","display_name":"UniDistance Suisse","ror":"https://ror.org/03exthx58","country_code":"CH","type":"education","lineage":["https://openalex.org/I4210134521"]},{"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":["UniDistance Suisse , Brig , Switzerland","Universit\u00e0 della Svizzera italiana , Lugano , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UniDistance Suisse , Brig , Switzerland","institution_ids":["https://openalex.org/I4210134521"]},{"raw_affiliation_string":"Universit\u00e0 della Svizzera italiana , Lugano , Switzerland","institution_ids":["https://openalex.org/I57201433"]}]}],"institutions":[],"countries_distinct_count":1,"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":0.9843999743461609,"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":0.9843999743461609,"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/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.007799999788403511,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.0032999999821186066,"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/trust-region-method","display_name":"trust region method","score":0.8690000176429749},{"id":"https://openalex.org/keywords/neural-network-training","display_name":"neural network training","score":0.9710000157356262},{"id":"https://openalex.org/keywords/parallel-optimization","display_name":"parallel optimization","score":0.5960000157356262},{"id":"https://openalex.org/keywords/preconditioning","display_name":"preconditioning","score":0.640999972820282},{"id":"https://openalex.org/keywords/global-convergence","display_name":"global convergence","score":0.8199999928474426}],"concepts":[{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.9390829801559448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7578692436218262},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.717494010925293},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.714526891708374},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.5248637199401855},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44744426012039185},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4374939799308777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4324076771736145},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35241222381591797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17189592123031616},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.13677","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.13677","pdf_url":"https://arxiv.org/pdf/2312.13677","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.13677","doi":"https://doi.org/10.48550/arxiv.2312.13677","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.13677","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:2312.13677","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.13677","pdf_url":"https://arxiv.org/pdf/2312.13677","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/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"},{"id":"https://openalex.org/G8717535088","display_name":"Multilevel training of DeepONets - multiscale and multiphysics applications","funder_award_id":"206745","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/W4390136752.pdf","grobid_xml":"https://content.openalex.org/works/W4390136752.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2523246573","https://openalex.org/W2785523195","https://openalex.org/W2900167092","https://openalex.org/W2902123811","https://openalex.org/W2964121744","https://openalex.org/W3158565736","https://openalex.org/W4306177574","https://openalex.org/W4311653698","https://openalex.org/W4394714806","https://openalex.org/W4402242033"],"related_works":["https://openalex.org/W4409704506","https://openalex.org/W4409777889","https://openalex.org/W7161269321","https://openalex.org/W1531238071","https://openalex.org/W2138893625","https://openalex.org/W2785602206","https://openalex.org/W2346438296","https://openalex.org/W2128206198","https://openalex.org/W4387947087","https://openalex.org/W2143962094"],"abstract_inverted_index":{"We":[0,72],"propose":[1],"to":[2,31],"train":[3],"neural":[4,33],"networks":[5],"(NNs)":[6],"using":[7],"a":[8,24,48,87,97],"novel":[9],"variant":[10],"of":[11,79,89],"the":[12,32,38,41,53,61,66,74,80,110],"``Additively":[13],"Preconditioned":[14],"Trust-region":[15],"Strategy''":[16],"(APTS).":[17],"The":[18,92],"proposed":[19,81],"method":[20,43,84],"is":[21],"based":[22],"on":[23],"parallelizable":[25],"additive":[26],"domain":[27],"decomposition":[28],"approach":[29],"applied":[30],"network's":[34],"parameters.":[35],"Built":[36],"upon":[37],"TR":[39,62,112],"framework,":[40],"APTS":[42,82],"ensures":[44],"global":[45],"convergence":[46],"towards":[47],"minimizer.":[49],"Moreover,":[50],"it":[51],"eliminates":[52],"need":[54],"for":[55],"computationally":[56],"expensive":[57],"hyper-parameter":[58],"tuning,":[59],"as":[60,105],"algorithm":[63],"automatically":[64],"determines":[65],"step":[67],"size":[68],"in":[69],"each":[70],"iteration.":[71],"demonstrate":[73],"capabilities,":[75],"strengths,":[76],"and":[77,109],"limitations":[78],"training":[83,102],"by":[85],"performing":[86],"series":[88],"numerical":[90,94],"experiments.":[91],"presented":[93],"study":[95],"includes":[96],"comparison":[98],"with":[99],"widely":[100],"used":[101],"methods":[103],"such":[104],"SGD,":[106],"Adam,":[107],"LBFGS,":[108],"standard":[111],"method.":[113]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-12-23T00:00:00"}