{"id":"https://openalex.org/W4315588858","doi":"https://doi.org/10.48550/arxiv.2301.03236","title":"Optimistic Meta-Gradients","display_name":"Optimistic Meta-Gradients","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4315588858","doi":"https://doi.org/10.48550/arxiv.2301.03236"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2301.03236","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.03236","pdf_url":"https://arxiv.org/pdf/2301.03236","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2301.03236","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001118898","display_name":"Sebastian Flennerhag","orcid":"https://orcid.org/0000-0003-2354-4193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Flennerhag, Sebastian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018613019","display_name":"Tom Zahavy","orcid":"https://orcid.org/0009-0009-2309-922X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zahavy, Tom","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027179922","display_name":"Brendan O\u2019Donoghue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"O'Donoghue, Brendan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033135596","display_name":"Hado van Hasselt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"van Hasselt, Hado","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041609088","display_name":"Andr\u00e1s Gy\u00f6rgy","orcid":"https://orcid.org/0000-0003-0586-4337"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gy\u00f6rgy, Andr\u00e1s","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065366930","display_name":"Satinder Singh","orcid":"https://orcid.org/0000-0002-2736-7641"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singh, Satinder","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9929999709129333,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9929999709129333,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9696999788284302,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9625999927520752,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.760500431060791},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6818720102310181},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.615093469619751},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6145704388618469},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.6070868372917175},{"id":"https://openalex.org/keywords/optimism","display_name":"Optimism","score":0.5537694692611694},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5116131901741028},{"id":"https://openalex.org/keywords/connection","display_name":"Connection (principal bundle)","score":0.5089535713195801},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49982428550720215},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49006545543670654},{"id":"https://openalex.org/keywords/meta-analysis","display_name":"Meta-analysis","score":0.4486255943775177},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.4392396807670593},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3207300901412964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29136979579925537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28725600242614746},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16390493512153625},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1380883753299713},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11516427993774414},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.10938888788223267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1006852388381958},{"id":"https://openalex.org/keywords/classical-mechanics","display_name":"Classical mechanics","score":0.09873303771018982}],"concepts":[{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.760500431060791},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6818720102310181},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.615093469619751},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6145704388618469},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.6070868372917175},{"id":"https://openalex.org/C204017024","wikidata":"https://www.wikidata.org/wiki/Q485446","display_name":"Optimism","level":2,"score":0.5537694692611694},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5116131901741028},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.5089535713195801},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49982428550720215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49006545543670654},{"id":"https://openalex.org/C95190672","wikidata":"https://www.wikidata.org/wiki/Q815382","display_name":"Meta-analysis","level":2,"score":0.4486255943775177},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.4392396807670593},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3207300901412964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29136979579925537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28725600242614746},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16390493512153625},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1380883753299713},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11516427993774414},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.10938888788223267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1006852388381958},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.09873303771018982},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2301.03236","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.03236","pdf_url":"https://arxiv.org/pdf/2301.03236","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2301.03236","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2301.03236","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.03236","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.03236","pdf_url":"https://arxiv.org/pdf/2301.03236","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/W4315588858.pdf","grobid_xml":"https://content.openalex.org/works/W4315588858.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2122713011","https://openalex.org/W2071729956","https://openalex.org/W2900331548","https://openalex.org/W2965399423","https://openalex.org/W2116758642","https://openalex.org/W4247284515","https://openalex.org/W2171209533","https://openalex.org/W3133545257","https://openalex.org/W3090423162","https://openalex.org/W2162941631"],"abstract_inverted_index":{"We":[0,10,67],"study":[1],"the":[2,37],"connection":[3],"between":[4],"gradient-based":[5],"meta-learning":[6,35,72],"and":[7,23],"convex":[8],"op-timisation.":[9],"observe":[11],"that":[12,69],"gradient":[13],"descent":[14],"with":[15],"momentum":[16],"is":[17,55,65],"a":[18,42],"special":[19],"case":[20],"of":[21,63],"meta-gradients,":[22],"building":[24],"on":[25],"recent":[26],"results":[27],"in":[28,36,71],"optimisation,":[29],"we":[30],"prove":[31],"convergence":[32,49],"rates":[33],"for":[34,58],"single":[38],"task":[39],"setting.":[40],"While":[41],"meta-learned":[43],"update":[44],"rule":[45],"can":[46,73],"yield":[47],"faster":[48],"up":[50],"to":[51],"constant":[52],"factor,":[53],"it":[54],"not":[56],"sufficient":[57],"acceleration.":[59],"Instead,":[60],"some":[61],"form":[62],"optimism":[64,70],"required.":[66],"show":[68],"be":[74],"captured":[75],"through":[76],"Bootstrapped":[77],"Meta-Gradients":[78],"(Flennerhag":[79],"et":[80],"al.,":[81],"2022),":[82],"providing":[83],"deeper":[84],"insight":[85],"into":[86],"its":[87],"underlying":[88],"mechanics.":[89]},"counts_by_year":[],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}