{"id":"https://openalex.org/W7165891066","doi":"https://doi.org/10.48550/arxiv.2606.25601","title":"Statistically Valid Post-Training Hyperparameter Selection: From Tuning to Guarantees","display_name":"Statistically Valid Post-Training Hyperparameter Selection: From Tuning to Guarantees","publication_year":2026,"publication_date":"2026-06-24","ids":{"openalex":"https://openalex.org/W7165891066","doi":"https://doi.org/10.48550/arxiv.2606.25601"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2606.25601","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.25601","pdf_url":"https://arxiv.org/pdf/2606.25601","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":"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.25601","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124276661","display_name":"Amirmohammad Farzaneh","orcid":"https://orcid.org/0000-0003-1928-6005","observed_orcids":["https://orcid.org/0000-0003-1928-6005"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farzaneh, Amirmohammad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126495032","display_name":"Osvaldo Simeone","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simeone, Osvaldo","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":3,"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":0.8384000062942505,"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":0.8384000062942505,"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/T10136","display_name":"Statistical Methods and Inference","score":0.03359999880194664,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.031300000846385956,"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/multiple-testing","display_name":"multiple comparisons","score":0.9909999966621399},{"id":"https://openalex.org/keywords/statistical-guarantees","display_name":"statistical guarantees","score":0.6779999732971191},{"id":"https://openalex.org/keywords/p-values","display_name":"p-values","score":0.8009999990463257},{"id":"https://openalex.org/keywords/e-values","display_name":"E-value","score":0.9980000257492065},{"id":"https://openalex.org/keywords/concentration-inequalities","display_name":"concentration inequalities","score":0.9769999980926514},{"id":"https://openalex.org/keywords/information-theoretic-constraints","display_name":"information-theoretic constraints","score":0.7720000147819519},{"id":"https://openalex.org/keywords/reliability-requirements","display_name":"reliability requirements","score":0.3479999899864197}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8899000287055969},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.8076000213623047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6263999938964844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5752000212669373},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5392000079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5252000093460083},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.358599990606308},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2606.25601","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.25601","pdf_url":"https://arxiv.org/pdf/2606.25601","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":"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.2606.25601","doi":"https://doi.org/10.48550/arxiv.2606.25601","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25601","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23801065","doi":"https://doi.org/10.5281/zenodo.23801065","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23801065","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23801066","doi":"https://doi.org/10.5281/zenodo.23801066","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23801066","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.25601","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.25601","pdf_url":"https://arxiv.org/pdf/2606.25601","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":"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5419401992","display_name":"FreeML: Engineering Networked Machine Learning via Meta-Free Energy Minimisation","funder_award_id":"EP/W024101/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8699128427","display_name":"ECCS-EPSRC: NeuroComm: Brain-Inspired Wireless Communications -- From Theoretical Foundations to Implementation for 6G and Beyond","funder_award_id":"EP/X011852/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7165891066.pdf","grobid_xml":"https://content.openalex.org/works/W7165891066.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1686946872","https://openalex.org/W1786332878","https://openalex.org/W2462906003","https://openalex.org/W2557579533","https://openalex.org/W2750384547","https://openalex.org/W2921827989","https://openalex.org/W2938704169","https://openalex.org/W3001279689","https://openalex.org/W3022566517","https://openalex.org/W3087003407","https://openalex.org/W3126216366","https://openalex.org/W3195577433","https://openalex.org/W4245577611","https://openalex.org/W4287714048","https://openalex.org/W4297823373","https://openalex.org/W4388327685","https://openalex.org/W4394662461","https://openalex.org/W4399758642","https://openalex.org/W4401306886","https://openalex.org/W4403786830","https://openalex.org/W4403928482","https://openalex.org/W4414746430","https://openalex.org/W4414829968","https://openalex.org/W7120088840","https://openalex.org/W7123620673","https://openalex.org/W7126027345","https://openalex.org/W7128958687","https://openalex.org/W7132836432","https://openalex.org/W7133225605","https://openalex.org/W7165186817","https://openalex.org/W7197047392"],"related_works":["https://openalex.org/W7108708118","https://openalex.org/W4403786830","https://openalex.org/W4403721464","https://openalex.org/W2808368578","https://openalex.org/W7097200507","https://openalex.org/W2886919371","https://openalex.org/W4389363970","https://openalex.org/W4241531010","https://openalex.org/W2272044563","https://openalex.org/W2145465275"],"abstract_inverted_index":{"Post-training":[0],"hyperparameter":[1,41,88,99],"selection":[2,42,100],"is":[3,43,151],"a":[4,81,107],"critical":[5],"step":[6],"in":[7],"the":[8,16,92,98,115],"deployment":[9],"of":[10,21,23,73,110,117,138],"modern":[11],"artificial":[12],"intelligence":[13],"systems,":[14],"given":[15],"need":[17],"to":[18],"tune":[19],"degrees":[20],"freedom":[22],"pre-trained":[24],"models":[25],"such":[26,50],"as":[27,51,102,125],"inference-time":[28],"parameters,":[29],"implementation-level":[30],"settings,":[31],"and":[32,76,148],"thresholds":[33],"driving":[34],"decision":[35],"rules.":[36],"Despite":[37],"its":[38],"practical":[39],"importance,":[40],"typically":[44],"performed":[45],"using":[46],"best-effort":[47],"empirical":[48],"methods":[49],"grid":[52],"search":[53],"or":[54,65,132],"Bayesian":[55],"optimization,":[56],"which":[57],"provide":[58],"no":[59],"formal":[60],"statistical":[61,83,143],"guarantees":[62],"on":[63,91,127],"reliability":[64,123],"safety.":[66],"This":[67],"monograph,":[68],"intended":[69],"for":[70,85],"an":[71],"audience":[72],"signal":[74],"processing":[75],"machine":[77],"learning":[78],"researchers,":[79],"presents":[80],"unified":[82],"framework":[84,113],"reliable":[86],"post-training":[87],"selection,":[89],"centered":[90],"learn-then-test":[93],"(LTT)":[94],"paradigm.":[95],"LTT":[96],"formulates":[97],"problem":[101],"multiple":[103],"hypothesis":[104],"testing":[105],"over":[106],"candidate":[108],"set":[109],"hyperparameters.":[111],"The":[112,141],"enables":[114],"choice":[116],"hyperparameters":[118],"that":[119],"provably":[120],"satisfy":[121],"application-specific":[122],"requirements---such":[124],"bounds":[126],"average":[128],"risk,":[129,131],"quantile":[130],"information-theoretic":[133],"constraints---with":[134],"explicit,":[135],"finite-sample":[136],"control":[137],"error":[139],"probabilities.":[140],"supporting":[142],"machinery,":[144],"namely":[145],"p-values,":[146],"e-values,":[147],"concentration":[149],"inequalities,":[150],"developed":[152],"from":[153],"first":[154],"principles.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-06-26T00:00:00"}