{"id":"https://openalex.org/W6928854522","doi":"https://doi.org/10.3929/ethz-b-000662390","title":"Meta-Learning Priors from Limited Data: From Theory to Practice","display_name":"Meta-Learning Priors from Limited Data: From Theory to Practice","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6928854522","doi":"https://doi.org/10.3929/ethz-b-000662390"},"language":"en","primary_location":{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/662390","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11850/662390","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"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":"info:eu-repo/semantics/doctoralThesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.3929/ethz-b-000662390","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rothfuss, Jonas","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rothfuss, Jonas","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":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":true,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.4781000018119812,"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":0.4781000018119812,"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":0.2980000078678131,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.04500000178813934,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/prior-probability","display_name":"Prior probability","score":0.8145999908447266},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6646000146865845},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.506600022315979},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.490200012922287},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4350000023841858},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4043999910354614},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.39989998936653137},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.8145999908447266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955999732017517},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6646000146865845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.645799994468689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6155999898910522},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.506600022315979},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3637999892234802},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C197352929","wikidata":"https://www.wikidata.org/wiki/Q1074074","display_name":"Inductive bias","level":4,"score":0.31459999084472656},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.31060001254081726},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.26420000195503235}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/662390","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11850/662390","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"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":"info:eu-repo/semantics/doctoralThesis"},{"id":"doi:10.3929/ethz-b-000662390","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000662390","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"doi:10.3929/ethz-b-000662390","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000662390","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unlike":[0],"machine":[1,287],"learning":[2,21,173,214,288],"systems,":[3],"humans":[4],"can":[5,110],"learn":[6,29],"new":[7],"concepts":[8,31],"from":[9,65,113,251],"only":[10,95,114],"a":[11,61,66,96,115,123,136,179,211,227],"few":[12],"examples":[13],"and":[14,186,285,290],"efficiently":[15,217],"adapt":[16,33],"to":[17,28,34,55,94,126,151,158,205,221],"changing":[18,222],"circumstances.":[19],"Machine":[20],"systems":[22],"typically":[23,64],"require":[24],"magnitudes":[25],"more":[26],"data":[27],"similar":[30],"or":[32,84],"changes.":[35],"This":[36],"is":[37],"because":[38],"they":[39],"lack":[40],"domain-specific":[41,57],"prior":[42],"knowledge":[43],"(also":[44],"known":[45],"as":[46],"inductive":[47,58],"bias).":[48],"To":[49,174],"address":[50],"these":[51],"shortcomings,":[52],"meta-learning":[53,73,191,229,241],"aims":[54],"acquire":[56],"bias":[59],"in":[60,75,88,103,129,182,197,243,280],"data-driven":[62],"way,":[63],"set":[67],"of":[68,82,99,117,138,261,273],"related":[69],"datasets.":[70,86,101,118,153],"Most":[71],"existing":[72],"approaches":[74,276],"the":[76,152,161,183,189,203,234,244,252,257,265,270],"literature":[77],"rely":[78],"on":[79,132],"an":[80],"abundance":[81],"domain-":[83],"problem-specific":[85],"However,":[87],"practice,":[89],"we":[90,106,109,121,134,177,201,209,225,267],"often":[91],"have":[92],"access":[93],"limited":[97],"number":[98],"such":[100],"Hence,":[102],"this":[104,175],"dissertation,":[105,266],"ask":[107],"how":[108],"successfully":[111],"meta-learn":[112,142],"handful":[116],"Addressing":[119],"this,":[120,133],"develop":[122],"theoretical":[124],"framework":[125,230],"understand":[127],"generalization":[128],"meta-learning.":[130],"Building":[131],"propose":[135,178,226],"class":[137],"scalable":[139],"algorithms":[140],"that":[141,148,160,188,231],"priors":[143,163,255],"with":[144,254,277],"principled":[145],"meta-level":[146],"regularization":[147,180],"prevents":[149],"overfitting":[150],"We":[154],"then":[155],"investigate":[156],"methods":[157],"ensure":[159],"meta-learned":[162],"provide":[164],"reliable":[165],"uncertainty":[166],"estimates,":[167],"making":[168],"them":[169],"suitable":[170],"for":[171,216],"interactive":[172],"end,":[176],"scheme":[181],"function":[184,245],"space":[185,260],"demonstrate":[187,269],"resulting":[190],"method":[192],"yields":[193],"significant":[194],"efficiency":[195],"gains":[196],"Bayesian":[198],"Optimization.":[199],"Subsequently,":[200],"extend":[202],"approach":[204,215],"safety-constraint":[206],"settings.":[207],"Furthermore,":[208],"introduce":[210],"model-based":[212],"meta-reinforcement":[213],"adapting":[218],"control":[219],"policies":[220],"dynamics.":[223],"Finally,":[224],"novel":[228],"directly":[232],"approximates":[233],"data-generating":[235],"stochastic":[236],"process.":[237],"As":[238],"it":[239,247],"formulates":[240],"entirely":[242],"space,":[246],"does":[248],"not":[249],"suffer":[250],"issues":[253],"over":[256],"high-dimensional":[258],"parameter":[259],"neural":[262],"networks.":[263],"Throughout":[264],"empirically":[268],"practical":[271],"efficacy":[272],"our":[274],"proposed":[275],"real-world":[278],"applications":[279],"health":[281],"care,":[282],"molecular":[283],"biology":[284],"automated":[286],"(AutoML),":[289],"robotic":[291],"control.":[292]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}