{"id":"https://openalex.org/W2886907189","doi":"https://doi.org/10.48550/arxiv.1808.02433","title":"Robust Implicit Backpropagation","display_name":"Robust Implicit Backpropagation","publication_year":2018,"publication_date":"2018-08-07","ids":{"openalex":"https://openalex.org/W2886907189","doi":"https://doi.org/10.48550/arxiv.1808.02433","mag":"2886907189"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1808.02433","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.02433","pdf_url":"https://arxiv.org/pdf/1808.02433","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":"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/1808.02433","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003144510","display_name":"Francois Fagan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fagan, Francois","raw_affiliation_strings":["Columbia University New York , NY , 10027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University New York , NY , 10027","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998274","display_name":"Garud Iyengar","orcid":"https://orcid.org/0000-0001-6546-4154","observed_orcids":["https://orcid.org/0000-0001-6546-4154"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iyengar, Garud","raw_affiliation_strings":["Columbia University New York , NY , 10027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University New York , NY , 10027","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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":0.9965999722480774,"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":0.9965999722480774,"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/T10320","display_name":"Neural Networks and Applications","score":0.00279999990016222,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.00019999999494757503,"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/neural-network-training","display_name":"neural network training","score":0.8970000147819519},{"id":"https://openalex.org/keywords/unconditional-stability","display_name":"unconditional stability","score":0.6299999952316284},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.6679999828338623}],"concepts":[{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.9162833094596863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652835845947266},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.716193437576294},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6878241300582886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5674364566802979},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5414502620697021},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4837341606616974},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4560660123825073},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4367740750312805},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42884087562561035},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40120911598205566},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05177828669548035},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1808.02433","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.02433","pdf_url":"https://arxiv.org/pdf/1808.02433","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2886907189","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1808.02433","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1808.02433","doi":"https://doi.org/10.48550/arxiv.1808.02433","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.02433","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:1808.02433","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.02433","pdf_url":"https://arxiv.org/pdf/1808.02433","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":"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/W2886907189.pdf","grobid_xml":"https://content.openalex.org/works/W2886907189.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W196761320","https://openalex.org/W644527247","https://openalex.org/W1522301498","https://openalex.org/W1546297643","https://openalex.org/W1819710477","https://openalex.org/W1902934009","https://openalex.org/W2146502635","https://openalex.org/W2157998899","https://openalex.org/W2238333240","https://openalex.org/W2593002563","https://openalex.org/W2593083167","https://openalex.org/W2602608495","https://openalex.org/W2604676813","https://openalex.org/W2624413595","https://openalex.org/W2695988161","https://openalex.org/W2749928749","https://openalex.org/W2774129214","https://openalex.org/W2949608212","https://openalex.org/W2964121744","https://openalex.org/W3037282472"],"related_works":["https://openalex.org/W2788763169","https://openalex.org/W2997914419","https://openalex.org/W2118264366","https://openalex.org/W4221111714","https://openalex.org/W2474828585","https://openalex.org/W2750786826","https://openalex.org/W2050107185","https://openalex.org/W2789621689","https://openalex.org/W2980680952","https://openalex.org/W4378765302"],"abstract_inverted_index":{"Arguably":[0],"the":[1,10,14,20,26,32,39,65],"biggest":[2],"challenge":[3],"in":[4,12,55],"applying":[5],"neural":[6,50,84],"networks":[7],"is":[8,23,71,91],"tuning":[9],"hyperparameters,":[11],"particular":[13],"learning":[15,21,66,96],"rate.":[16,67],"The":[17],"sensitivity":[18],"to":[19,25,30,48,58,64,94],"rate":[22],"due":[24],"reliance":[27],"on":[28,103],"backpropagation":[29,102],"train":[31,49],"network.":[33],"In":[34],"this":[35],"paper":[36],"we":[37],"present":[38],"first":[40],"application":[41],"of":[42,76,106],"Implicit":[43],"Stochastic":[44],"Gradient":[45],"Descent":[46],"(ISGD)":[47],"networks,":[51],"a":[52,72,104],"method":[53,90],"known":[54],"convex":[56],"optimization":[57],"be":[59],"unconditionally":[60],"stable":[61],"and":[62,98],"robust":[63,93],"Our":[68],"key":[69],"contribution":[70],"novel":[73],"layer-wise":[74],"approximation":[75],"ISGD":[77],"which":[78],"makes":[79],"its":[80],"updates":[81],"tractable":[82],"for":[83],"networks.":[85],"Experiments":[86],"show":[87],"that":[88],"our":[89],"more":[92],"high":[95],"rates":[97],"generally":[99],"outperforms":[100],"standard":[101],"variety":[105],"tasks.":[107]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-08-22T00:00:00"}