{"id":"https://openalex.org/W3014430345","doi":"https://doi.org/10.24963/ijcai.2020/293","title":"Marthe: Scheduling the Learning Rate Via Online Hypergradients","display_name":"Marthe: Scheduling the Learning Rate Via Online Hypergradients","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3014430345","doi":"https://doi.org/10.24963/ijcai.2020/293","mag":"3014430345"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/293","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/293","pdf_url":"https://www.ijcai.org/proceedings/2020/0293.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0293.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056775618","display_name":"Michele Donini","orcid":"https://orcid.org/0000-0002-9769-3899"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michele Donini","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074874504","display_name":"Luca Franceschi","orcid":"https://orcid.org/0000-0002-1810-1016"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB","IT"],"is_corresponding":false,"raw_author_name":"Luca Franceschi","raw_affiliation_strings":["Istituto Italiano di Tecnologia","University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060729969","display_name":"Orchid Majumder","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Orchid Majumder","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034260726","display_name":"Massimiliano Pontil","orcid":"https://orcid.org/0000-0001-9415-098X"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB","IT"],"is_corresponding":false,"raw_author_name":"Massimiliano Pontil","raw_affiliation_strings":["Istituto Italiano di Tecnologia","University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027422071","display_name":"Paolo Frasconi","orcid":"https://orcid.org/0000-0003-3117-9245"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Frasconi","raw_affiliation_strings":["Universit\u00e0 di Firenze"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Firenze","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2119","last_page":"2125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9988999962806702,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9988999962806702,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7696924209594727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7287805080413818},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5796992182731628},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5333077311515808},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.5314188003540039},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5283689498901367},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5281617045402527},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5106266140937805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5002110004425049},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49628502130508423},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47094807028770447},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4239349365234375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17451590299606323},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16119250655174255}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7696924209594727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287805080413818},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5796992182731628},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5333077311515808},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.5314188003540039},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5283689498901367},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5281617045402527},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5106266140937805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5002110004425049},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49628502130508423},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47094807028770447},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4239349365234375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17451590299606323},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16119250655174255},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":5,"locations":[{"id":"doi:10.24963/ijcai.2020/293","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/293","pdf_url":"https://www.ijcai.org/proceedings/2020/0293.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.08525","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.08525","pdf_url":"https://arxiv.org/pdf/1910.08525","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:3014430345","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.08525.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:flore.unifi.it:2158/1214703","is_oa":true,"landing_page_url":"http://hdl.handle.net/2158/1214703","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1910.08525","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.08525","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":"Preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/293","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/293","pdf_url":"https://www.ijcai.org/proceedings/2020/0293.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3014430345.pdf","grobid_xml":"https://content.openalex.org/works/W3014430345.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W24696228","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1585773866","https://openalex.org/W1672060489","https://openalex.org/W1806891645","https://openalex.org/W1836465849","https://openalex.org/W2006903949","https://openalex.org/W2033245860","https://openalex.org/W2107878631","https://openalex.org/W2112796928","https://openalex.org/W2116628315","https://openalex.org/W2120420045","https://openalex.org/W2129142203","https://openalex.org/W2160208155","https://openalex.org/W2187061624","https://openalex.org/W2194775991","https://openalex.org/W2210969396","https://openalex.org/W2261408131","https://openalex.org/W2597452529","https://openalex.org/W2602585184","https://openalex.org/W2786615446","https://openalex.org/W2908974255","https://openalex.org/W2945800474","https://openalex.org/W2950182411","https://openalex.org/W2950728319","https://openalex.org/W2962826047","https://openalex.org/W2962835968","https://openalex.org/W2962961534","https://openalex.org/W2963233958","https://openalex.org/W2963263347","https://openalex.org/W2963306862","https://openalex.org/W2963775850","https://openalex.org/W2963804140","https://openalex.org/W2964029277","https://openalex.org/W2964155842","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W3131236796","https://openalex.org/W2962779867","https://openalex.org/W2901943723","https://openalex.org/W2818059595","https://openalex.org/W1533225923","https://openalex.org/W2917322258","https://openalex.org/W2144655553","https://openalex.org/W2945943081","https://openalex.org/W2808421695","https://openalex.org/W2767419258","https://openalex.org/W3037308930","https://openalex.org/W3130395087","https://openalex.org/W2950471160","https://openalex.org/W1492936035","https://openalex.org/W2783634529","https://openalex.org/W2101915445","https://openalex.org/W3126245445","https://openalex.org/W1600824415","https://openalex.org/W2024191559","https://openalex.org/W2949561945"],"abstract_inverted_index":{"We":[0,20],"study":[1],"the":[2,11,22,25,32,37,54,61],"problem":[3],"of":[4,13,24,27,53],"fitting":[5],"task-specific":[6],"learning":[7,33,90],"rate":[8,34,91],"schedules":[9,92],"from":[10,60],"perspective":[12],"hyperparameter":[14],"optimization,":[15],"aiming":[16],"at":[17],"good":[18],"generalization.":[19],"describe":[21],"structure":[23],"gradient":[26],"a":[28,45],"validation":[29],"error":[30],"w.r.t.":[31],"schedule":[35],"--":[36],"hypergradient.":[38],"Based":[39],"on":[40],"this,":[41],"we":[42],"introduce":[43],"MARTHE,":[44],"novel":[46],"online":[47],"algorithm":[48],"guided":[49],"by":[50],"cheap":[51],"approximations":[52],"hypergradient":[55],"that":[56,93,100],"uses":[57],"past":[58],"information":[59],"optimization":[62],"trajectory":[63],"to":[64,88,98],"simulate":[65],"future":[66],"behaviour.":[67],"It":[68],"interpolates":[69],"between":[70],"two":[71],"recent":[72],"techniques,":[73],"RTHO":[74],"(Franceschi":[75],"et":[76,82],"al.,":[77],"2017)":[78],"and":[79,85],"HD":[80],"(Baydin":[81],"al.":[83],"2018),":[84],"is":[86],"able":[87],"produce":[89],"are":[94],"more":[95],"stable":[96],"leading":[97],"models":[99],"generalize":[101],"better.":[102]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}