FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950277768> ?p ?o ?g. }

• W2950277768 abstract "Bayesian optimization is an effective methodology for the global optimization of functions with expensive evaluations. It relies on querying a distribution over functions defined by a relatively cheap surrogate model. An accurate model for this distribution over functions is critical to the effectiveness of the approach, and is typically fit using Gaussian processes (GPs). However, since GPs scale cubically with the number of observations, it has been challenging to handle objectives whose optimization requires many evaluations, and as such, massively parallelizing the optimization. In this work, we explore the use of neural networks as an alternative to GPs to model distributions over functions. We show that performing adaptive basis function regression with a neural network as the parametric form performs competitively with state-of-the-art GP-based approaches, but scales linearly with the number of data rather than cubically. This allows us to achieve a previously intractable degree of parallelism, which we apply to large scale hyperparameter optimization, rapidly finding competitive models on benchmark object recognition tasks using convolutional networks, and image caption generation using neural language models." @default.
• W2950277768 created "2019-06-27" @default.
• W2950277768 creator A5007769527 @default.
• W2950277768 creator A5022938074 @default.
• W2950277768 creator A5026208886 @default.
• W2950277768 creator A5029612014 @default.
• W2950277768 creator A5031913929 @default.
• W2950277768 creator A5041039212 @default.
• W2950277768 creator A5044982268 @default.
• W2950277768 creator A5048688625 @default.
• W2950277768 creator A5055166817 @default.
• W2950277768 date "2015-02-19" @default.
• W2950277768 modified "2023-09-27" @default.
• W2950277768 title "Scalable Bayesian Optimization Using Deep Neural Networks" @default.
• W2950277768 cites W137285897 @default.
• W2950277768 cites W1491420040 @default.
• W2950277768 cites W1514535095 @default.
• W2950277768 cites W1567512734 @default.
• W2950277768 cites W1701825639 @default.
• W2950277768 cites W1799366690 @default.
• W2950277768 cites W1844684489 @default.
• W2950277768 cites W1861492603 @default.
• W2950277768 cites W1871676304 @default.
• W2950277768 cites W1904365287 @default.
• W2950277768 cites W1959608418 @default.
• W2950277768 cites W2047229728 @default.
• W2950277768 cites W2073272667 @default.
• W2950277768 cites W2097998348 @default.
• W2950277768 cites W2099768828 @default.
• W2950277768 cites W2106411961 @default.
• W2950277768 cites W2111051539 @default.
• W2950277768 cites W2111241577 @default.
• W2950277768 cites W2113145584 @default.
• W2950277768 cites W2123045220 @default.
• W2950277768 cites W2139929624 @default.
• W2950277768 cites W2150394223 @default.
• W2950277768 cites W2151238122 @default.
• W2950277768 cites W2156375221 @default.
• W2950277768 cites W2157801062 @default.
• W2950277768 cites W2162724919 @default.
• W2950277768 cites W2168894214 @default.
• W2950277768 cites W2169003314 @default.
• W2950277768 cites W2171361956 @default.
• W2950277768 cites W2200000192 @default.
• W2950277768 cites W2402456051 @default.
• W2950277768 cites W2728797307 @default.
• W2950277768 cites W2949727204 @default.
• W2950277768 cites W2950178297 @default.
• W2950277768 cites W2950182411 @default.
• W2950277768 cites W2951665052 @default.
• W2950277768 cites W2952264928 @default.
• W2950277768 cites W2952677397 @default.
• W2950277768 cites W2952908320 @default.
• W2950277768 cites W2953308237 @default.
• W2950277768 cites W2963110737 @default.
• W2950277768 cites W3037265734 @default.
• W2950277768 cites W3037950864 @default.
• W2950277768 cites W4919037 @default.
• W2950277768 cites W60686164 @default.
• W2950277768 cites W76331760 @default.
• W2950277768 cites W84569508 @default.
• W2950277768 cites W884987551 @default.
• W2950277768 hasPublicationYear "2015" @default.
• W2950277768 type Work @default.
• W2950277768 sameAs 2950277768 @default.
• W2950277768 citedByCount "76" @default.
• W2950277768 countsByYear W29502777682014 @default.
• W2950277768 countsByYear W29502777682015 @default.
• W2950277768 countsByYear W29502777682016 @default.
• W2950277768 countsByYear W29502777682017 @default.
• W2950277768 countsByYear W29502777682018 @default.
• W2950277768 countsByYear W29502777682019 @default.
• W2950277768 countsByYear W29502777682020 @default.
• W2950277768 countsByYear W29502777682021 @default.
• W2950277768 crossrefType "posted-content" @default.
• W2950277768 hasAuthorship W2950277768A5007769527 @default.
• W2950277768 hasAuthorship W2950277768A5022938074 @default.
• W2950277768 hasAuthorship W2950277768A5026208886 @default.
• W2950277768 hasAuthorship W2950277768A5029612014 @default.
• W2950277768 hasAuthorship W2950277768A5031913929 @default.
• W2950277768 hasAuthorship W2950277768A5041039212 @default.
• W2950277768 hasAuthorship W2950277768A5044982268 @default.
• W2950277768 hasAuthorship W2950277768A5048688625 @default.
• W2950277768 hasAuthorship W2950277768A5055166817 @default.
• W2950277768 hasConcept C108583219 @default.
• W2950277768 hasConcept C11413529 @default.
• W2950277768 hasConcept C119857082 @default.
• W2950277768 hasConcept C121332964 @default.
• W2950277768 hasConcept C131675550 @default.
• W2950277768 hasConcept C13280743 @default.
• W2950277768 hasConcept C137836250 @default.
• W2950277768 hasConcept C154945302 @default.
• W2950277768 hasConcept C163716315 @default.
• W2950277768 hasConcept C185798385 @default.
• W2950277768 hasConcept C205649164 @default.
• W2950277768 hasConcept C2778049539 @default.
• W2950277768 hasConcept C41008148 @default.
• W2950277768 hasConcept C48044578 @default.
• W2950277768 hasConcept C50644808 @default.
• W2950277768 hasConcept C60229501 @default.

• next