{"id":"https://openalex.org/W2981024147","doi":"https://doi.org/10.48550/arxiv.1910.09464","title":"Learning to Learn by Zeroth-Order Oracle","display_name":"Learning to Learn by Zeroth-Order Oracle","publication_year":2019,"publication_date":"2019-10-21","ids":{"openalex":"https://openalex.org/W2981024147","doi":"https://doi.org/10.48550/arxiv.1910.09464","mag":"2981024147"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1910.09464","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09464","pdf_url":"https://arxiv.org/pdf/1910.09464","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.09464","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074108427","display_name":"Yangjun Ruan","orcid":"https://orcid.org/0000-0002-0816-219X","observed_orcids":["https://orcid.org/0000-0002-0816-219X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruan, Yangjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056336934","display_name":"Yuanhao Xiong","orcid":"https://orcid.org/0000-0002-0940-2079","observed_orcids":["https://orcid.org/0000-0002-0940-2079"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Yuanhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082314161","display_name":"Sashank Jakkam Reddi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reddi, Sashank","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018301052","display_name":"Sanjiv Kumar","orcid":"https://orcid.org/0000-0002-4080-1414","observed_orcids":["https://orcid.org/0000-0002-4080-1414"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Sanjiv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010841999","display_name":"Cho\u2010Jui Hsieh","orcid":"https://orcid.org/0000-0002-3520-9627","observed_orcids":["https://orcid.org/0000-0002-3520-9627"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsieh, Cho-Jui","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":false,"cited_by_count":9,"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":0.9916999936103821,"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":0.9916999936103821,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0020000000949949026,"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":0.0007999999797903001,"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/meta-learning","display_name":"meta-learning","score":0.9900000095367432},{"id":"https://openalex.org/keywords/derivative-free-optimization","display_name":"derivative-free optimization","score":0.9819999933242798},{"id":"https://openalex.org/keywords/learned-optimizers","display_name":"learned optimizers","score":0.7799999713897705},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.8399999737739563},{"id":"https://openalex.org/keywords/gradient-estimation","display_name":"gradient estimation","score":0.5730000138282776},{"id":"https://openalex.org/keywords/gaussian-sampling","display_name":"Gaussian sampling","score":0.5870000123977661},{"id":"https://openalex.org/keywords/black-box-adversarial-attacks","display_name":"black-box adversarial attacks","score":0.8180000185966492},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.5730000138282776}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7256556153297424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7252451777458191},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.617112934589386},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.51668381690979},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5078039765357971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47147420048713684},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4538591504096985},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4472372531890869},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4154520332813263},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4152989685535431},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40990135073661804},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39844071865081787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38760024309158325},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15944388508796692},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1910.09464","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09464","pdf_url":"https://arxiv.org/pdf/1910.09464","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":"doi:10.48550/arxiv.1910.09464","doi":"https://doi.org/10.48550/arxiv.1910.09464","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.09464","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"},{"id":"mag:2996506051","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.09464.pdf","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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.09464","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09464","pdf_url":"https://arxiv.org/pdf/1910.09464","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W1980411262","https://openalex.org/W2149479912","https://openalex.org/W2162953669","https://openalex.org/W2166160300","https://openalex.org/W2171830216","https://openalex.org/W2409744450","https://openalex.org/W2427497464","https://openalex.org/W2516574342","https://openalex.org/W2560100619","https://openalex.org/W2593649546","https://openalex.org/W2602585184","https://openalex.org/W2603766943","https://openalex.org/W2604451232","https://openalex.org/W2624086852","https://openalex.org/W2746600820","https://openalex.org/W2807044327","https://openalex.org/W2874797877","https://openalex.org/W2913235840","https://openalex.org/W2946774369","https://openalex.org/W2951004968","https://openalex.org/W2963243330","https://openalex.org/W2963470657","https://openalex.org/W2963483475","https://openalex.org/W2964205597","https://openalex.org/W4324106947"],"related_works":["https://openalex.org/W3153338775","https://openalex.org/W2966868123","https://openalex.org/W7161539466","https://openalex.org/W4408236039","https://openalex.org/W4407128146","https://openalex.org/W4387356156","https://openalex.org/W7221521832","https://openalex.org/W6925524917","https://openalex.org/W4392579614","https://openalex.org/W4407729147"],"abstract_inverted_index":{"In":[0,29],"the":[1,9,26,34,71,93,100,128,137,153],"learning":[2,17],"to":[3,24,37,82,91,151],"learn":[4,25,92],"(L2L)":[5],"framework,":[6],"we":[7,32,86],"cast":[8],"design":[10],"of":[11,73,112,136,142,155],"optimization":[12,40,124],"algorithms":[13,109],"as":[14,53],"a":[15],"machine":[16],"problem":[18],"and":[19,65,97,115,121],"use":[20],"deep":[21],"neural":[22,55],"networks":[23],"update":[27,69],"rules.":[28],"this":[30],"paper,":[31],"extend":[33],"L2L":[35],"framework":[36],"zeroth-order":[38],"(ZO)":[39],"setting,":[41],"where":[42],"no":[43],"explicit":[44],"gradient":[45,60,63,84],"information":[46],"is":[47,134],"available.":[48],"Our":[49,104],"learned":[50,105],"optimizer,":[51],"modeled":[52],"recurrent":[54],"network":[56],"(RNN),":[57],"first":[58],"approximates":[59],"by":[61],"ZO":[62,83,123,143],"estimator":[64],"then":[66],"produces":[67],"parameter":[68],"utilizing":[70],"knowledge":[72],"previous":[74],"iterations.":[75],"To":[76],"reduce":[77],"high":[78],"variance":[79],"effect":[80],"due":[81],"estimator,":[85],"further":[87],"introduce":[88],"another":[89],"RNN":[90],"Gaussian":[94],"sampling":[95],"rule":[96],"dynamically":[98],"guide":[99],"query":[101],"direction":[102],"sampling.":[103],"optimizer":[106],"outperforms":[107],"hand-designed":[108],"in":[110],"terms":[111],"convergence":[113],"rate":[114],"final":[116],"solution":[117],"on":[118],"both":[119],"synthetic":[120],"practical":[122],"tasks":[125,141],"(in":[126],"particular,":[127],"black-box":[129],"adversarial":[130],"attack":[131],"task,":[132],"which":[133],"one":[135],"most":[138],"widely":[139],"used":[140],"optimization).":[144],"We":[145],"finally":[146],"conduct":[147],"extensive":[148],"analytical":[149],"experiments":[150],"demonstrate":[152],"effectiveness":[154],"our":[156],"proposed":[157],"optimizer.":[158]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2019-10-25T00:00:00"}