{"id":"https://openalex.org/W2895642264","doi":"https://doi.org/10.1007/978-3-030-01424-7_39","title":"Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio","display_name":"Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2895642264","doi":"https://doi.org/10.1007/978-3-030-01424-7_39","mag":"2895642264"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-01424-7_39","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-01424-7_39","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/1b1d210a-efed-44b7-8907-c1506f70a64d","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024552077","display_name":"Stanis\u0142aw Jastrz\u0229bski","orcid":"https://orcid.org/0000-0003-4138-1818"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA","PL"],"is_corresponding":false,"raw_author_name":"Stanislaw Jastrz\u0119bski","raw_affiliation_strings":["Facebook AI Research, Paris, France","Jagiellonian University, Krak\u00f3w, Poland","MILA, Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Paris, France","institution_ids":[]},{"raw_affiliation_string":"Jagiellonian University, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I126596746"]},{"raw_affiliation_string":"MILA, Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069438696","display_name":"Zachary Kenton","orcid":null},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA","PL"],"is_corresponding":false,"raw_author_name":"Zachary Kenton","raw_affiliation_strings":["Jagiellonian University, Krak\u00f3w, Poland","MILA, Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jagiellonian University, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I126596746"]},{"raw_affiliation_string":"MILA, Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000111662","display_name":"Devansh Arpit","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Devansh Arpit","raw_affiliation_strings":["MILA, Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MILA, Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057065873","display_name":"Nicolas Ballas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Ballas","raw_affiliation_strings":["Facebook AI Research, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Paris, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026151059","display_name":"Asja Fischer","orcid":"https://orcid.org/0000-0002-1916-7033"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Asja Fischer","raw_affiliation_strings":["Faculty of Mathematics, Ruhr-University Bochum, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics, Ruhr-University Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I109736498","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95","country_code":"CA","type":"facility","lineage":["https://openalex.org/I109736498"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["CIFAR Senior Fellow, Toronto, Canada","MILA, Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIFAR Senior Fellow, Toronto, Canada","institution_ids":["https://openalex.org/I109736498"]},{"raw_affiliation_string":"MILA, Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007901825","display_name":"Amos Storkey","orcid":"https://orcid.org/0000-0002-8100-506X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Amos Storkey","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, Scotland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, Scotland","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"392","last_page":"402"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","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"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","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/T10320","display_name":"Neural Networks and Applications","score":0.9977999925613403,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9969000220298767,"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/maxima-and-minima","display_name":"Maxima and minima","score":0.9182946681976318},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.8093979954719543},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7651249170303345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.683286190032959},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.638809323310852},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5779041647911072},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5121512413024902},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5090369582176208},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.48229363560676575},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.46938344836235046},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46913760900497437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4284172058105469},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4236929714679718},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41994738578796387},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3221508264541626},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22576865553855896},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.12973245978355408},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10776534676551819}],"concepts":[{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.9182946681976318},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.8093979954719543},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7651249170303345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.683286190032959},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.638809323310852},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5779041647911072},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5121512413024902},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5090369582176208},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.48229363560676575},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.46938344836235046},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46913760900497437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4284172058105469},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4236929714679718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41994738578796387},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3221508264541626},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22576865553855896},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.12973245978355408},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10776534676551819},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-030-01424-7_39","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-01424-7_39","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:pure.ed.ac.uk:publications/1b1d210a-efed-44b7-8907-c1506f70a64d","is_oa":true,"landing_page_url":"https://link.springer.com/chapter/10.1007/978-3-030-01424-7_39","pdf_url":"https://www.research.ed.ac.uk/en/publications/1b1d210a-efed-44b7-8907-c1506f70a64d","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/1b1d210a-efed-44b7-8907-c1506f70a64d","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/1b1d210a-efed-44b7-8907-c1506f70a64d","pdf_url":"https://www.research.ed.ac.uk/files/75846467/width_of_minima_reached_by_stochastic_gradient_descent_is_influenced_by_learning_rate_to_batch_size_ratio.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":null,"raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/1b1d210a-efed-44b7-8907-c1506f70a64d","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/1b1d210a-efed-44b7-8907-c1506f70a64d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":null,"raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/1b1d210a-efed-44b7-8907-c1506f70a64d","is_oa":true,"landing_page_url":"https://link.springer.com/chapter/10.1007/978-3-030-01424-7_39","pdf_url":"https://www.research.ed.ac.uk/en/publications/1b1d210a-efed-44b7-8907-c1506f70a64d","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2249529433","display_name":"Platform for Open Development of Systems of Artificial Intelligence","funder_award_id":"732204","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320994","display_name":"Canada Research Chairs","ror":"https://ror.org/0517h6h17"},{"id":"https://openalex.org/F4320330273","display_name":"Institut de Valorisation des Donn\u00e9es","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2895642264.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1575104486","https://openalex.org/W1686810756","https://openalex.org/W2167433878","https://openalex.org/W2605488176","https://openalex.org/W2617242334","https://openalex.org/W2618076303","https://openalex.org/W2622263826","https://openalex.org/W2626325961","https://openalex.org/W2682189153","https://openalex.org/W2750384547","https://openalex.org/W2782476368","https://openalex.org/W2790626470","https://openalex.org/W2912811302","https://openalex.org/W2963177640","https://openalex.org/W2963959597","https://openalex.org/W2964072432","https://openalex.org/W4231021340","https://openalex.org/W6600503824","https://openalex.org/W6600737549","https://openalex.org/W6740005241"],"related_works":["https://openalex.org/W2115886818","https://openalex.org/W3118431319","https://openalex.org/W3004700632","https://openalex.org/W2466106906","https://openalex.org/W3177888558","https://openalex.org/W3027810930","https://openalex.org/W2069187387","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}