{"id":"https://openalex.org/W3003481009","doi":"https://doi.org/10.1109/ciss48834.2020.1570617381","title":"MSE-Optimal Neural Network Initialization via Layer Fusion","display_name":"MSE-Optimal Neural Network Initialization via Layer Fusion","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3003481009","doi":"https://doi.org/10.1109/ciss48834.2020.1570617381","mag":"3003481009"},"language":"en","primary_location":{"id":"doi:10.1109/ciss48834.2020.1570617381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss48834.2020.1570617381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 54th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.10509","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089959870","display_name":"Ramina Ghods","orcid":"https://orcid.org/0000-0001-8401-380X"},"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":true,"raw_author_name":"Ramina Ghods","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063813962","display_name":"Andrew Lan","orcid":"https://orcid.org/0000-0002-8475-6600"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew S. Lan","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA","University of Massachusetts, Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060687985","display_name":"Tom Goldstein","orcid":"https://orcid.org/0000-0003-1660-9307"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Goldstein","raw_affiliation_strings":["University of Maryland, College Park, MD","University of Maryland - College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland - College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083617223","display_name":"Christoph Studer","orcid":"https://orcid.org/0000-0001-8950-6267"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christoph Studer","raw_affiliation_strings":["Cornell Tech, New York, NY","cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell Tech, New York, NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089959870"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0981,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36319629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9995999932289124,"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/initialization","display_name":"Initialization","score":0.9707651138305664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7586047649383545},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5893773436546326},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.549227237701416},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5398920774459839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5352030396461487},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4944586753845215},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.46189606189727783},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44597533345222473},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4149949252605438},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4147462844848633},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36980947852134705},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36879634857177734}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.9707651138305664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7586047649383545},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5893773436546326},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.549227237701416},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5398920774459839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5352030396461487},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4944586753845215},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.46189606189727783},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44597533345222473},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4149949252605438},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4147462844848633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36980947852134705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36879634857177734},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/ciss48834.2020.1570617381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss48834.2020.1570617381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 54th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.10509","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.10509","pdf_url":"https://arxiv.org/pdf/2001.10509","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"mag:3003481009","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2001.10509.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/452589","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/452589","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"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":"2020 54th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2001.10509","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.10509","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},{"id":"doi:10.3929/ethz-b-000452589","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000452589","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.10509","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.10509","pdf_url":"https://arxiv.org/pdf/2001.10509","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W134960717","https://openalex.org/W1521591241","https://openalex.org/W1533861849","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1724438581","https://openalex.org/W1821462560","https://openalex.org/W1935978687","https://openalex.org/W2094644779","https://openalex.org/W2097117768","https://openalex.org/W2114766824","https://openalex.org/W2120972216","https://openalex.org/W2125389748","https://openalex.org/W2125930537","https://openalex.org/W2134797427","https://openalex.org/W2161591461","https://openalex.org/W2163605009","https://openalex.org/W2167215970","https://openalex.org/W2178237821","https://openalex.org/W2612445135","https://openalex.org/W2750384547","https://openalex.org/W2788800397","https://openalex.org/W2797583228","https://openalex.org/W2884034421","https://openalex.org/W2899748887","https://openalex.org/W2963114950","https://openalex.org/W2963163009","https://openalex.org/W2963236897","https://openalex.org/W2963374099","https://openalex.org/W2963674932","https://openalex.org/W2963759574","https://openalex.org/W2963981420","https://openalex.org/W2964299589","https://openalex.org/W3021036476","https://openalex.org/W3118608800","https://openalex.org/W3137695714","https://openalex.org/W6605479355","https://openalex.org/W6631398929","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6637709462","https://openalex.org/W6638523607","https://openalex.org/W6638783484","https://openalex.org/W6639703010","https://openalex.org/W6640289440","https://openalex.org/W6677103964","https://openalex.org/W6677580257","https://openalex.org/W6678000929","https://openalex.org/W6678583879","https://openalex.org/W6678818196","https://openalex.org/W6679909955","https://openalex.org/W6681017033","https://openalex.org/W6683826617","https://openalex.org/W6684191040","https://openalex.org/W6684563725","https://openalex.org/W6685315510","https://openalex.org/W6724998850","https://openalex.org/W6737664043","https://openalex.org/W6743688258","https://openalex.org/W6748581759","https://openalex.org/W6748600614","https://openalex.org/W6750665317","https://openalex.org/W6763485134","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W3021036476","https://openalex.org/W3174185214","https://openalex.org/W2472117222","https://openalex.org/W1989422077","https://openalex.org/W2916965824","https://openalex.org/W3019371514","https://openalex.org/W3021623424","https://openalex.org/W2963397124","https://openalex.org/W3098895240","https://openalex.org/W2949413532","https://openalex.org/W2404774341","https://openalex.org/W2905801789","https://openalex.org/W3040425217","https://openalex.org/W2762534372","https://openalex.org/W2964113612","https://openalex.org/W2951401169","https://openalex.org/W2952645228","https://openalex.org/W2743024835","https://openalex.org/W3006614220","https://openalex.org/W2952004933"],"abstract_inverted_index":{"Deep":[0],"neural":[1,120],"networks":[2,71,78,121,129],"achieve":[3],"state-of-the-art":[4],"performance":[5],"for":[6,92,108],"a":[7,40,65,109],"range":[8,110],"of":[9,17,25,42,76,98,111],"classification":[10,112],"and":[11,89,102,113,127],"inference":[12],"tasks.":[13],"However,":[14],"the":[15,23,26,57],"use":[16],"stochastic":[18],"gradient":[19],"descent":[20],"combined":[21],"with":[22,82,142],"nonconvexity":[24],"underlying":[27],"optimization":[28],"problems":[29],"renders":[30],"parameter":[31,48],"learning":[32],"susceptible":[33],"to":[34,68,125],"initialization.":[35,84],"To":[36],"address":[37],"this":[38,60],"issue,":[39],"variety":[41],"methods":[43],"that":[44,79,118],"rely":[45],"on":[46],"random":[47,83],"initialization":[49,126],"or":[50],"knowledge":[51],"distillation":[52],"have":[53],"been":[54],"proposed":[55],"in":[56],"past.":[58],"In":[59],"paper,":[61],"we":[62],"propose":[63],"FuseInit,":[64],"novel":[66],"method":[67],"initialize":[69],"shallower":[70,128],"by":[72],"fusing":[73],"neighboring":[74,99],"layers":[75],"deeper":[77,119,138],"are":[80,122],"trained":[81],"We":[85,105],"develop":[86],"theoretical":[87],"results":[88],"efficient":[90],"algorithms":[91],"mean-square":[93],"error":[94],"(MSE)-":[95],"optimal":[96],"fusion":[97],"dense-dense,":[100],"convolutional-dense,":[101],"convolutional-convolutional":[103],"layers.":[104],"show":[106],"experiments":[107],"regression":[114],"datasets,":[115],"which":[116],"suggest":[117],"less":[123],"sensitive":[124],"can":[130],"perform":[131],"better":[132],"(sometimes":[133],"as":[134,136],"well":[135],"their":[137],"counterparts)":[139],"if":[140],"initialized":[141],"FuseInit.":[143]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}