FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2556372419> ?p ?o ?g. }

• W2556372419 endingPage "4149" @default.
• W2556372419 startingPage "4141" @default.
• W2556372419 abstract "Bayesian optimization is a prominent method for optimizing expensive-to-evaluate black-box functions that is widely applied to tuning the hyperparameters of machine learning algorithms. Despite its successes, the prototypical Bayesian optimization approach - using Gaussian process models - does not scale well to either many hyperparameters or many function evaluations. Attacking this lack of scalability and flexibility is thus one of the key challenges of the field. We present a general approach for using flexible parametric models (neural networks) for Bayesian optimization, staying as close to a truly Bayesian treatment as possible. We obtain scalability through stochastic gradient Hamiltonian Monte Carlo, whose robustness we improve via a scale adaptation. Experiments including multi-task Bayesian optimization with 21 tasks, parallel optimization of deep neural networks and deep reinforcement learning show the power and flexibility of this approach." @default.
• W2556372419 created "2016-11-30" @default.
• W2556372419 creator A5017985443 @default.
• W2556372419 creator A5031002895 @default.
• W2556372419 creator A5044806693 @default.
• W2556372419 creator A5089220005 @default.
• W2556372419 date "2016-12-05" @default.
• W2556372419 modified "2023-09-24" @default.
• W2556372419 title "Bayesian optimization with robust Bayesian neural networks" @default.
• W2556372419 cites W1510052597 @default.
• W2556372419 cites W1524172054 @default.
• W2556372419 cites W1545319692 @default.
• W2556372419 cites W1567512734 @default.
• W2556372419 cites W1569788011 @default.
• W2556372419 cites W1719489212 @default.
• W2556372419 cites W1798702550 @default.
• W2556372419 cites W2059448777 @default.
• W2556372419 cites W2099201756 @default.
• W2556372419 cites W2106411961 @default.
• W2556372419 cites W2108677974 @default.
• W2556372419 cites W2113145584 @default.
• W2556372419 cites W2120420045 @default.
• W2556372419 cites W2132862423 @default.
• W2556372419 cites W2144193737 @default.
• W2556372419 cites W2146502635 @default.
• W2556372419 cites W2164411961 @default.
• W2556372419 cites W2194775991 @default.
• W2556372419 cites W2200000192 @default.
• W2556372419 cites W2238987678 @default.
• W2556372419 cites W2276300401 @default.
• W2556372419 cites W2290354866 @default.
• W2556372419 cites W2408019865 @default.
• W2556372419 cites W2950182411 @default.
• W2556372419 cites W2951266961 @default.
• W2556372419 cites W2951595529 @default.
• W2556372419 cites W2951654389 @default.
• W2556372419 cites W2963864421 @default.
• W2556372419 cites W2964059111 @default.
• W2556372419 cites W3124229194 @default.
• W2556372419 cites W60686164 @default.
• W2556372419 cites W74059680 @default.
• W2556372419 hasPublicationYear "2016" @default.
• W2556372419 type Work @default.
• W2556372419 sameAs 2556372419 @default.
• W2556372419 citedByCount "149" @default.
• W2556372419 countsByYear W25563724192016 @default.
• W2556372419 countsByYear W25563724192017 @default.
• W2556372419 countsByYear W25563724192018 @default.
• W2556372419 countsByYear W25563724192019 @default.
• W2556372419 countsByYear W25563724192020 @default.
• W2556372419 countsByYear W25563724192021 @default.
• W2556372419 countsByYear W25563724192022 @default.
• W2556372419 crossrefType "proceedings-article" @default.
• W2556372419 hasAuthorship W2556372419A5017985443 @default.
• W2556372419 hasAuthorship W2556372419A5031002895 @default.
• W2556372419 hasAuthorship W2556372419A5044806693 @default.
• W2556372419 hasAuthorship W2556372419A5089220005 @default.
• W2556372419 hasConcept C107673813 @default.
• W2556372419 hasConcept C119857082 @default.
• W2556372419 hasConcept C121332964 @default.
• W2556372419 hasConcept C154945302 @default.
• W2556372419 hasConcept C160234255 @default.
• W2556372419 hasConcept C163716315 @default.
• W2556372419 hasConcept C2778049539 @default.
• W2556372419 hasConcept C41008148 @default.
• W2556372419 hasConcept C50644808 @default.
• W2556372419 hasConcept C61326573 @default.
• W2556372419 hasConcept C62520636 @default.
• W2556372419 hasConcept C71983512 @default.
• W2556372419 hasConcept C8642999 @default.
• W2556372419 hasConceptScore W2556372419C107673813 @default.
• W2556372419 hasConceptScore W2556372419C119857082 @default.
• W2556372419 hasConceptScore W2556372419C121332964 @default.
• W2556372419 hasConceptScore W2556372419C154945302 @default.
• W2556372419 hasConceptScore W2556372419C160234255 @default.
• W2556372419 hasConceptScore W2556372419C163716315 @default.
• W2556372419 hasConceptScore W2556372419C2778049539 @default.
• W2556372419 hasConceptScore W2556372419C41008148 @default.
• W2556372419 hasConceptScore W2556372419C50644808 @default.
• W2556372419 hasConceptScore W2556372419C61326573 @default.
• W2556372419 hasConceptScore W2556372419C62520636 @default.
• W2556372419 hasConceptScore W2556372419C71983512 @default.
• W2556372419 hasConceptScore W2556372419C8642999 @default.
• W2556372419 hasLocation W25563724191 @default.
• W2556372419 hasOpenAccess W2556372419 @default.
• W2556372419 hasPrimaryLocation W25563724191 @default.
• W2556372419 hasRelatedWork W1510052597 @default.
• W2556372419 hasRelatedWork W1746819321 @default.
• W2556372419 hasRelatedWork W1798702550 @default.
• W2556372419 hasRelatedWork W2097998348 @default.
• W2556372419 hasRelatedWork W2099201756 @default.
• W2556372419 hasRelatedWork W2106411961 @default.
• W2556372419 hasRelatedWork W2113145584 @default.
• W2556372419 hasRelatedWork W2131241448 @default.
• W2556372419 hasRelatedWork W2192203593 @default.
• W2556372419 hasRelatedWork W2194775991 @default.
• W2556372419 hasRelatedWork W2200000192 @default.
• W2556372419 hasRelatedWork W2873705236 @default.

• next