{"id":"https://openalex.org/W7204014834","doi":null,"title":"Reducing Manual Intervention in Deep Learning","display_name":"Reducing Manual Intervention in Deep Learning","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7204014834"},"language":"en","primary_location":{"id":"pmh:oai:utoronto.scholaris.ca:1807/153836","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1807/153836","pdf_url":"https://utoronto.scholaris.ca/bitstreams/19511fd8-edbf-4ee1-8aa8-882e31d83f66/download","source":{"id":"https://openalex.org/S4306400261","display_name":"TSpace (University of Toronto)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I185261750","host_organization_name":"University of Toronto","host_organization_lineage":["https://openalex.org/I185261750"],"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":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://utoronto.scholaris.ca/bitstreams/19511fd8-edbf-4ee1-8aa8-882e31d83f66/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147853133","display_name":"Michael Ruoqi Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zhang, Michael Ruoqi","raw_affiliation_strings":["Department of Computer Science University of Toronto 2026"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Toronto 2026","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5147853133"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"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/T12535","display_name":"Machine Learning and Data Classification","score":0.986299991607666,"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":0.986299991607666,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.00800000037997961,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0012000000569969416,"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/automated-machine-learning","display_name":"automated machine learning","score":0.8880000114440918},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.953000009059906},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8009999990463257},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.953000009059906},{"id":"https://openalex.org/keywords/hypernetworks","display_name":"hypernetworks","score":0.9779999852180481},{"id":"https://openalex.org/keywords/rate-distortion-trade-off","display_name":"rate-distortion tradeoff","score":0.875},{"id":"https://openalex.org/keywords/report-cards","display_name":"school reports","score":0.6660000085830688}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8496000170707703},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7663999795913696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7574999928474426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480000257492065},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.65420001745224},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.5067999958992004},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.358599990606308},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3059999942779541},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:utoronto.scholaris.ca:1807/153836","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1807/153836","pdf_url":"https://utoronto.scholaris.ca/bitstreams/19511fd8-edbf-4ee1-8aa8-882e31d83f66/download","source":{"id":"https://openalex.org/S4306400261","display_name":"TSpace (University of Toronto)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I185261750","host_organization_name":"University of Toronto","host_organization_lineage":["https://openalex.org/I185261750"],"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":"Thesis"}],"best_oa_location":{"id":"pmh:oai:utoronto.scholaris.ca:1807/153836","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1807/153836","pdf_url":"https://utoronto.scholaris.ca/bitstreams/19511fd8-edbf-4ee1-8aa8-882e31d83f66/download","source":{"id":"https://openalex.org/S4306400261","display_name":"TSpace (University of Toronto)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I185261750","host_organization_name":"University of Toronto","host_organization_lineage":["https://openalex.org/I185261750"],"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":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204014834.pdf","grobid_xml":"https://content.openalex.org/works/W7204014834.grobid-xml"},"referenced_works_count":96,"referenced_works":["https://openalex.org/W1686946872","https://openalex.org/W1836465849","https://openalex.org/W1959608418","https://openalex.org/W2112796928","https://openalex.org/W2210838531","https://openalex.org/W2518108298","https://openalex.org/W2557579533","https://openalex.org/W2560512785","https://openalex.org/W2622263826","https://openalex.org/W2743945814","https://openalex.org/W2746314669","https://openalex.org/W2786022758","https://openalex.org/W2786615446","https://openalex.org/W2788838181","https://openalex.org/W2792287754","https://openalex.org/W2795900505","https://openalex.org/W2797328513","https://openalex.org/W2799054028","https://openalex.org/W2806800515","https://openalex.org/W2807692250","https://openalex.org/W2808305757","https://openalex.org/W2884711234","https://openalex.org/W2893749619","https://openalex.org/W2903771406","https://openalex.org/W2907670343","https://openalex.org/W2907938015","https://openalex.org/W2908510526","https://openalex.org/W2910135751","https://openalex.org/W2922007426","https://openalex.org/W2948350736","https://openalex.org/W2950344723","https://openalex.org/W2951670304","https://openalex.org/W2951696961","https://openalex.org/W2959756691","https://openalex.org/W2963651499","https://openalex.org/W2967237190","https://openalex.org/W2967791890","https://openalex.org/W2995291884","https://openalex.org/W3001279689","https://openalex.org/W3037932933","https://openalex.org/W3083410900","https://openalex.org/W3126325318","https://openalex.org/W3131330854","https://openalex.org/W3200635595","https://openalex.org/W3215529831","https://openalex.org/W4283028517","https://openalex.org/W4293566159","https://openalex.org/W4307207785","https://openalex.org/W4312050653","https://openalex.org/W4320003957","https://openalex.org/W4322718191","https://openalex.org/W4327810158","https://openalex.org/W4360836968","https://openalex.org/W4362703233","https://openalex.org/W4365563505","https://openalex.org/W4366999185","https://openalex.org/W4372272770","https://openalex.org/W4384918448","https://openalex.org/W4385327568","https://openalex.org/W4385573190","https://openalex.org/W4386554921","https://openalex.org/W4387031363","https://openalex.org/W4387389783","https://openalex.org/W4387561528","https://openalex.org/W4389344855","https://openalex.org/W4389518874","https://openalex.org/W4389519254","https://openalex.org/W4391506243","https://openalex.org/W4392616695","https://openalex.org/W4394642966","https://openalex.org/W4394662461","https://openalex.org/W4394708144","https://openalex.org/W4398192849","https://openalex.org/W4399453597","https://openalex.org/W4399837985","https://openalex.org/W4400611750","https://openalex.org/W4401043381","https://openalex.org/W4401043863","https://openalex.org/W4401306886","https://openalex.org/W4402502966","https://openalex.org/W4402667059","https://openalex.org/W4402671302","https://openalex.org/W4402952666","https://openalex.org/W4402954103","https://openalex.org/W4403578729","https://openalex.org/W4410559688","https://openalex.org/W4410915308","https://openalex.org/W4415108068","https://openalex.org/W4415795211","https://openalex.org/W4415797148","https://openalex.org/W4417172194","https://openalex.org/W7133188930","https://openalex.org/W7133212451","https://openalex.org/W7133224126","https://openalex.org/W7133224573","https://openalex.org/W7133242745"],"related_works":["https://openalex.org/W7081571979","https://openalex.org/W4409126833","https://openalex.org/W7160294057","https://openalex.org/W2210969396","https://openalex.org/W3164686416","https://openalex.org/W7129076919","https://openalex.org/W7045624599","https://openalex.org/W4391631249","https://openalex.org/W4392205891","https://openalex.org/W3011655242"],"abstract_inverted_index":{"Deep":[0],"learning":[1,50,212,221],"practitioners":[2],"face":[3],"numerous":[4],"manual":[5,202],"decisions":[6,23],"throughout":[7],"the":[8,48,113,120,139,143,216],"model":[9,20,35,181,188],"development":[10],"pipeline,":[11],"from":[12,231],"selecting":[13],"hyperparameters":[14],"and":[15,28,55,134,141,156],"optimization":[16],"algorithms":[17],"to":[18,33,98,118,137,161,186,225],"evaluating":[19],"capabilities.":[21],"These":[22],"often":[24],"require":[25,200],"extensive":[26,201],"expertise":[27],"computational":[29,229],"resources,":[30],"creating":[31],"barriers":[32],"effective":[34],"development.":[36],"We":[37,65],"present":[38,126],"approaches":[39,80],"for":[40,115],"reducing":[41,228],"human":[42],"intervention":[43],"across":[44,102,153],"three":[45],"stages":[46],"of":[47,145,179,218],"deep":[49,211],"pipeline:":[51],"hyperparameter":[52,58,164],"selection,":[53,59],"optimization,":[54,124],"evaluation.":[56],"For":[57,87,123,166],"we":[60,91,125,168],"explore":[61,119],"two":[62],"complementary":[63],"approaches.":[64],"show":[66],"that":[67,130,197,222],"large":[68],"language":[69,177,180],"models":[70],"(LLMs)":[71],"can":[72],"effectively":[73],"suggest":[74],"hyperparameters,":[75],"matching":[76],"or":[77],"outperforming":[78],"classical":[79],"on":[81],"standard":[82],"benchmarks":[83],"with":[84],"limited":[85],"budgets.":[86],"variational":[88],"autoencoders":[89],"specifically,":[90],"introduce":[92],"Multi-Rate":[93],"VAE,":[94],"which":[95,172],"uses":[96],"hypernetworks":[97],"learn":[99],"optimal":[100],"parameters":[101],"all":[103],"KL":[104],"weight":[105],"values":[106],"in":[107,210],"a":[108],"single":[109],"training":[110],"run,":[111],"eliminating":[112],"need":[114],"repeated":[116],"experiments":[117],"rate-distortion":[121],"tradeoff.":[122],"Lookahead,":[127],"an":[128,146],"algorithm":[129],"iteratively":[131],"updates":[132],"slow":[133],"fast":[135],"weights":[136],"reduce":[138],"variance":[140],"improve":[142],"stability":[144],"inner":[147],"optimizer.":[148],"Lookahead":[149],"consistently":[150],"improves":[151],"convergence":[152],"diverse":[154],"architectures":[155],"tasks":[157],"while":[158,227],"remaining":[159],"robust":[160],"its":[162],"own":[163],"choices.":[165],"evaluation,":[167],"propose":[169],"Report":[170,190],"Cards,":[171],"are":[173],"automatically":[174],"generated":[175],"natural":[176],"summaries":[178],"behavior.":[182],"By":[183],"using":[184],"LLMs":[185],"analyze":[187],"outputs,":[189],"Cards":[191],"complement":[192],"traditional":[193],"metrics,":[194],"providing":[195],"insights":[196],"would":[198],"typically":[199],"analysis.":[203],"Together,":[204],"these":[205],"methods":[206],"address":[207],"key":[208],"bottlenecks":[209],"workflows,":[213],"working":[214],"toward":[215],"vision":[217],"automated":[219],"machine":[220],"is":[223],"accessible":[224],"non-experts":[226],"waste":[230],"trial-and-error":[232],"experimentation.":[233]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-23T00:00:00"}