Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890918712> ?p ?o ?g. }
- W2890918712 abstract "Bayesian optimization usually assumes that a Bayesian prior is given. However, the strong theoretical guarantees in Bayesian optimization are often regrettably compromised in practice because of unknown parameters in the prior. In this paper, we adopt a variant of empirical Bayes and show that, by estimating the Gaussian process prior from offline data sampled from the same prior and constructing unbiased estimators of the posterior, variants of both GP-UCB and probability of improvement achieve a near-zero regret bound, which decreases to a constant proportional to the observational noise as the number of offline data and the number of online evaluations increase. Empirically, we have verified our approach on challenging simulated robotic problems featuring task and motion planning." @default.
- W2890918712 created "2018-09-27" @default.
- W2890918712 creator A5012862284 @default.
- W2890918712 creator A5030337320 @default.
- W2890918712 creator A5043315280 @default.
- W2890918712 date "2018-11-23" @default.
- W2890918712 modified "2023-09-22" @default.
- W2890918712 title "Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior" @default.
- W2890918712 cites W122178443 @default.
- W2890918712 cites W1517567737 @default.
- W2890918712 cites W1529817821 @default.
- W2890918712 cites W1560153690 @default.
- W2890918712 cites W1567512734 @default.
- W2890918712 cites W174371023 @default.
- W2890918712 cites W1976422186 @default.
- W2890918712 cites W1999040315 @default.
- W2890918712 cites W2061144551 @default.
- W2890918712 cites W2111241577 @default.
- W2890918712 cites W2113145584 @default.
- W2890918712 cites W2130283669 @default.
- W2890918712 cites W2139805416 @default.
- W2890918712 cites W2151554678 @default.
- W2890918712 cites W2157118346 @default.
- W2890918712 cites W2167789032 @default.
- W2890918712 cites W2169178495 @default.
- W2890918712 cites W2200000192 @default.
- W2890918712 cites W2324309783 @default.
- W2890918712 cites W2555374257 @default.
- W2890918712 cites W2594441185 @default.
- W2890918712 cites W2732547613 @default.
- W2890918712 cites W2785444061 @default.
- W2890918712 cites W2788853733 @default.
- W2890918712 cites W2950103693 @default.
- W2890918712 cites W2950182411 @default.
- W2890918712 cites W2951665052 @default.
- W2890918712 cites W2962958357 @default.
- W2890918712 cites W2963238274 @default.
- W2890918712 cites W2963742654 @default.
- W2890918712 cites W46565623 @default.
- W2890918712 cites W574441371 @default.
- W2890918712 hasPublicationYear "2018" @default.
- W2890918712 type Work @default.
- W2890918712 sameAs 2890918712 @default.
- W2890918712 citedByCount "3" @default.
- W2890918712 countsByYear W28909187122018 @default.
- W2890918712 countsByYear W28909187122020 @default.
- W2890918712 crossrefType "posted-content" @default.
- W2890918712 hasAuthorship W2890918712A5012862284 @default.
- W2890918712 hasAuthorship W2890918712A5030337320 @default.
- W2890918712 hasAuthorship W2890918712A5043315280 @default.
- W2890918712 hasConcept C105795698 @default.
- W2890918712 hasConcept C107673813 @default.
- W2890918712 hasConcept C11413529 @default.
- W2890918712 hasConcept C119857082 @default.
- W2890918712 hasConcept C121332964 @default.
- W2890918712 hasConcept C126255220 @default.
- W2890918712 hasConcept C154945302 @default.
- W2890918712 hasConcept C163716315 @default.
- W2890918712 hasConcept C185429906 @default.
- W2890918712 hasConcept C207201462 @default.
- W2890918712 hasConcept C2778049539 @default.
- W2890918712 hasConcept C33923547 @default.
- W2890918712 hasConcept C41008148 @default.
- W2890918712 hasConcept C50817715 @default.
- W2890918712 hasConcept C61326573 @default.
- W2890918712 hasConcept C62520636 @default.
- W2890918712 hasConcept C73602740 @default.
- W2890918712 hasConceptScore W2890918712C105795698 @default.
- W2890918712 hasConceptScore W2890918712C107673813 @default.
- W2890918712 hasConceptScore W2890918712C11413529 @default.
- W2890918712 hasConceptScore W2890918712C119857082 @default.
- W2890918712 hasConceptScore W2890918712C121332964 @default.
- W2890918712 hasConceptScore W2890918712C126255220 @default.
- W2890918712 hasConceptScore W2890918712C154945302 @default.
- W2890918712 hasConceptScore W2890918712C163716315 @default.
- W2890918712 hasConceptScore W2890918712C185429906 @default.
- W2890918712 hasConceptScore W2890918712C207201462 @default.
- W2890918712 hasConceptScore W2890918712C2778049539 @default.
- W2890918712 hasConceptScore W2890918712C33923547 @default.
- W2890918712 hasConceptScore W2890918712C41008148 @default.
- W2890918712 hasConceptScore W2890918712C50817715 @default.
- W2890918712 hasConceptScore W2890918712C61326573 @default.
- W2890918712 hasConceptScore W2890918712C62520636 @default.
- W2890918712 hasConceptScore W2890918712C73602740 @default.
- W2890918712 hasLocation W28909187121 @default.
- W2890918712 hasOpenAccess W2890918712 @default.
- W2890918712 hasPrimaryLocation W28909187121 @default.
- W2890918712 hasRelatedWork W2033271913 @default.
- W2890918712 hasRelatedWork W2164376925 @default.
- W2890918712 hasRelatedWork W2605744708 @default.
- W2890918712 hasRelatedWork W2752086744 @default.
- W2890918712 hasRelatedWork W2782644035 @default.
- W2890918712 hasRelatedWork W2911859348 @default.
- W2890918712 hasRelatedWork W2912819213 @default.
- W2890918712 hasRelatedWork W2963273374 @default.
- W2890918712 hasRelatedWork W2995924146 @default.
- W2890918712 hasRelatedWork W2998984630 @default.
- W2890918712 hasRelatedWork W3026374127 @default.
- W2890918712 hasRelatedWork W3082274400 @default.
- W2890918712 hasRelatedWork W3106195168 @default.