FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1535019556> ?p ?o ?g. }

• W1535019556 endingPage "927" @default.
• W1535019556 startingPage "918" @default.
• W1535019556 abstract "Bayesian optimization is a powerful tool for fine-tuning the hyper-parameters of a wide variety of machine learning models. The success of machine learning has led practitioners in diverse real-world settings to learn classifiers for practical problems. As machine learning becomes commonplace, Bayesian optimization becomes an attractive method for practitioners to automate the process of classifier hyper-parameter tuning. A key observation is that the data used for tuning models in these settings is often sensitive. Certain data such as genetic predisposition, personal email statistics, and car accident history, if not properly private, may be at risk of being inferred from Bayesian optimization outputs. To address this, we introduce methods for releasing the best hyper-parameters and classifier accuracy privately. Leveraging the strong theoretical guarantees of differential privacy and known Bayesian optimization convergence bounds, we prove that under a GP assumption these private quantities are often near-optimal. Finally, even if this assumption is not satisfied, we can use different smoothness guarantees to protect privacy." @default.
• W1535019556 created "2016-06-24" @default.
• W1535019556 creator A5006380227 @default.
• W1535019556 creator A5013647396 @default.
• W1535019556 creator A5017894606 @default.
• W1535019556 creator A5072585411 @default.
• W1535019556 date "2015-07-06" @default.
• W1535019556 modified "2023-09-26" @default.
• W1535019556 title "Differentially Private Bayesian Optimization" @default.
• W1535019556 cites W112690700 @default.
• W1535019556 cites W1557833142 @default.
• W1535019556 cites W1560724230 @default.
• W1535019556 cites W168548896 @default.
• W1535019556 cites W1746819321 @default.
• W1535019556 cites W1873763122 @default.
• W1535019556 cites W1975937116 @default.
• W1535019556 cites W1985511977 @default.
• W1535019556 cites W1993116423 @default.
• W1535019556 cites W2027595342 @default.
• W1535019556 cites W202805564 @default.
• W1535019556 cites W2053801139 @default.
• W1535019556 cites W2070996757 @default.
• W1535019556 cites W2078011655 @default.
• W1535019556 cites W2083961165 @default.
• W1535019556 cites W2097998348 @default.
• W1535019556 cites W2103492748 @default.
• W1535019556 cites W2104743167 @default.
• W1535019556 cites W2107976320 @default.
• W1535019556 cites W2110582581 @default.
• W1535019556 cites W2110868467 @default.
• W1535019556 cites W2113145584 @default.
• W1535019556 cites W2118075434 @default.
• W1535019556 cites W2119595900 @default.
• W1535019556 cites W2119821739 @default.
• W1535019556 cites W2119874464 @default.
• W1535019556 cites W2129157759 @default.
• W1535019556 cites W2131241448 @default.
• W1535019556 cites W2131824593 @default.
• W1535019556 cites W2133654650 @default.
• W1535019556 cites W2135930857 @default.
• W1535019556 cites W2150230313 @default.
• W1535019556 cites W2168405694 @default.
• W1535019556 cites W2170307371 @default.
• W1535019556 cites W2182267394 @default.
• W1535019556 cites W2399077675 @default.
• W1535019556 cites W2421405286 @default.
• W1535019556 cites W2951665052 @default.
• W1535019556 cites W2952908320 @default.
• W1535019556 cites W2963423011 @default.
• W1535019556 cites W2964064173 @default.
• W1535019556 cites W2964172739 @default.
• W1535019556 cites W60686164 @default.
• W1535019556 cites W76331760 @default.
• W1535019556 cites W92292672 @default.
• W1535019556 hasPublicationYear "2015" @default.
• W1535019556 type Work @default.
• W1535019556 sameAs 1535019556 @default.
• W1535019556 citedByCount "12" @default.
• W1535019556 countsByYear W15350195562018 @default.
• W1535019556 countsByYear W15350195562019 @default.
• W1535019556 countsByYear W15350195562020 @default.
• W1535019556 countsByYear W15350195562021 @default.
• W1535019556 countsByYear W15350195562022 @default.
• W1535019556 crossrefType "proceedings-article" @default.
• W1535019556 hasAuthorship W1535019556A5006380227 @default.
• W1535019556 hasAuthorship W1535019556A5013647396 @default.
• W1535019556 hasAuthorship W1535019556A5017894606 @default.
• W1535019556 hasAuthorship W1535019556A5072585411 @default.
• W1535019556 hasConcept C107673813 @default.
• W1535019556 hasConcept C11413529 @default.
• W1535019556 hasConcept C119857082 @default.
• W1535019556 hasConcept C124101348 @default.
• W1535019556 hasConcept C136197465 @default.
• W1535019556 hasConcept C137836250 @default.
• W1535019556 hasConcept C154945302 @default.
• W1535019556 hasConcept C23130292 @default.
• W1535019556 hasConcept C2778049539 @default.
• W1535019556 hasConcept C41008148 @default.
• W1535019556 hasConcept C95623464 @default.
• W1535019556 hasConceptScore W1535019556C107673813 @default.
• W1535019556 hasConceptScore W1535019556C11413529 @default.
• W1535019556 hasConceptScore W1535019556C119857082 @default.
• W1535019556 hasConceptScore W1535019556C124101348 @default.
• W1535019556 hasConceptScore W1535019556C136197465 @default.
• W1535019556 hasConceptScore W1535019556C137836250 @default.
• W1535019556 hasConceptScore W1535019556C154945302 @default.
• W1535019556 hasConceptScore W1535019556C23130292 @default.
• W1535019556 hasConceptScore W1535019556C2778049539 @default.
• W1535019556 hasConceptScore W1535019556C41008148 @default.
• W1535019556 hasConceptScore W1535019556C95623464 @default.
• W1535019556 hasLocation W15350195561 @default.
• W1535019556 hasOpenAccess W1535019556 @default.
• W1535019556 hasPrimaryLocation W15350195561 @default.
• W1535019556 hasRelatedWork W16521680 @default.
• W1535019556 hasRelatedWork W168548896 @default.
• W1535019556 hasRelatedWork W1873763122 @default.
• W1535019556 hasRelatedWork W1883147838 @default.
• W1535019556 hasRelatedWork W1985511977 @default.

• next