{"id":"https://openalex.org/W4389983385","doi":"https://doi.org/10.48550/arxiv.2312.10672","title":"Automatic Optimisation of Normalised Neural Networks","display_name":"Automatic Optimisation of Normalised Neural Networks","publication_year":2023,"publication_date":"2023-12-17","ids":{"openalex":"https://openalex.org/W4389983385","doi":"https://doi.org/10.48550/arxiv.2312.10672"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.10672","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.10672","pdf_url":"https://arxiv.org/pdf/2312.10672","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,"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.10672","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040511921","display_name":"Namhoon Cho","orcid":"https://orcid.org/0000-0001-9999-9501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cho, Namhoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001666073","display_name":"Hyo\u2010Sang Shin","orcid":"https://orcid.org/0000-0001-9938-0370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shin, Hyo-Sang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.9991999864578247,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14510","display_name":"Medical Imaging and Analysis","score":0.9702000021934509,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/artificial-neural-network","display_name":"Artificial neural network","score":0.6310602426528931},{"id":"https://openalex.org/keywords/hessian-matrix","display_name":"Hessian matrix","score":0.5606534481048584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5580736994743347},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.4840673506259918},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4778170883655548},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.46728023886680603},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.45711779594421387},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4184383749961853},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37727490067481995},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36059173941612244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34268712997436523},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.27709323167800903}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6310602426528931},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.5606534481048584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5580736994743347},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.4840673506259918},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4778170883655548},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.46728023886680603},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.45711779594421387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4184383749961853},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37727490067481995},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36059173941612244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34268712997436523},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.27709323167800903},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.10672","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.10672","pdf_url":"https://arxiv.org/pdf/2312.10672","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,"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.2312.10672","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.10672","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.10672","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.10672","pdf_url":"https://arxiv.org/pdf/2312.10672","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,"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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389983385.pdf","grobid_xml":"https://content.openalex.org/works/W4389983385.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2611031068","https://openalex.org/W1704347466","https://openalex.org/W4283017538","https://openalex.org/W2355987247","https://openalex.org/W4288346661","https://openalex.org/W2947416323","https://openalex.org/W4297883503","https://openalex.org/W4379474754","https://openalex.org/W2896257321","https://openalex.org/W3016975909"],"abstract_inverted_index":{"We":[0],"propose":[1,97],"automatic":[2,111],"optimisation":[3],"methods":[4,162],"considering":[5],"the":[6,12,30,40,52,56,61,65,69,73,78,92,103,114,118,123,141,147,160,169],"geometry":[7],"of":[8,15,64,91,113,126,140,168],"matrix":[9],"manifold":[10,125],"for":[11,45,105,153,177],"normalised":[13,179],"parameters":[14],"neural":[16,154,180],"networks.":[17,155,181],"Layerwise":[18],"weight":[19],"normalisation":[20],"with":[21,58],"respect":[22,59],"to":[23,28,34,60,101],"Frobenius":[24],"norm":[25],"is":[26],"utilised":[27,135],"bound":[29],"Lipschitz":[31],"constant":[32],"and":[33,54,166],"enhance":[35],"gradient":[36],"reliability":[37],"so":[38],"that":[39,90],"trained":[41],"networks":[42],"are":[43],"suitable":[44],"control":[46],"applications.":[47],"Our":[48],"approach":[49],"first":[50,108],"initialises":[51],"network":[53],"normalises":[55],"data":[57],"$\\ell^{2}$-$\\ell^{2}$":[62],"gain":[63],"initialised":[66],"network.":[67],"Then,":[68],"proposed":[70,161],"algorithms":[71],"take":[72],"update":[74,86,119],"structure":[75],"based":[76],"on":[77,81,122],"exponential":[79],"map":[80],"high-dimensional":[82],"spheres.":[83,127],"Given":[84],"an":[85,174],"direction":[87],"such":[88],"as":[89],"negative":[93],"Riemannian":[94],"gradient,":[95],"we":[96],"two":[98],"different":[99],"ways":[100],"determine":[102],"stepsize":[104],"descent.":[106],"The":[107,128,143],"algorithm":[109,145],"utilises":[110,146],"differentiation":[112],"objective":[115],"function":[116],"along":[117],"curve":[120],"defined":[121],"combined":[124],"directional":[129],"second-order":[130],"derivative":[131],"information":[132],"can":[133],"be":[134],"without":[136],"requiring":[137],"explicit":[138],"construction":[139],"Hessian.":[142],"second":[144],"majorisation-minimisation":[148],"framework":[149],"via":[150],"architecture-aware":[151],"majorisation":[152],"With":[156],"these":[157],"new":[158],"developments,":[159],"avoid":[163],"manual":[164],"tuning":[165],"scheduling":[167],"learning":[170],"rate,":[171],"thus":[172],"providing":[173],"automated":[175],"pipeline":[176],"optimizing":[178]},"counts_by_year":[],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-10-10T00:00:00"}