Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287202213> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4287202213 abstract "Bayesian optimization (BO) is a popular paradigm for global optimization of expensive black-box functions, but there are many domains where the function is not completely a black-box. The data may have some known structure (e.g. symmetries) and/or the data generation process may be a composite process that yields useful intermediate or auxiliary information in addition to the value of the optimization objective. However, surrogate models traditionally employed in BO, such as Gaussian Processes (GPs), scale poorly with dataset size and do not easily accommodate known structure. Instead, we use Bayesian neural networks, a class of scalable and flexible surrogate models with inductive biases, to extend BO to complex, structured problems with high dimensionality. We demonstrate BO on a number of realistic problems in physics and chemistry, including topology optimization of photonic crystal materials using convolutional neural networks, and chemical property optimization of molecules using graph neural networks. On these complex tasks, we show that neural networks often outperform GPs as surrogate models for BO in terms of both sampling efficiency and computational cost." @default.
- W4287202213 created "2022-07-25" @default.
- W4287202213 creator A5012957555 @default.
- W4287202213 creator A5032640764 @default.
- W4287202213 creator A5044982268 @default.
- W4287202213 creator A5047818475 @default.
- W4287202213 creator A5060426875 @default.
- W4287202213 creator A5080178929 @default.
- W4287202213 date "2021-04-23" @default.
- W4287202213 modified "2023-10-16" @default.
- W4287202213 title "Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structure" @default.
- W4287202213 doi "https://doi.org/10.48550/arxiv.2104.11667" @default.
- W4287202213 hasPublicationYear "2021" @default.
- W4287202213 type Work @default.
- W4287202213 citedByCount "0" @default.
- W4287202213 crossrefType "posted-content" @default.
- W4287202213 hasAuthorship W4287202213A5012957555 @default.
- W4287202213 hasAuthorship W4287202213A5032640764 @default.
- W4287202213 hasAuthorship W4287202213A5044982268 @default.
- W4287202213 hasAuthorship W4287202213A5047818475 @default.
- W4287202213 hasAuthorship W4287202213A5060426875 @default.
- W4287202213 hasAuthorship W4287202213A5080178929 @default.
- W4287202213 hasBestOaLocation W42872022131 @default.
- W4287202213 hasConcept C108583219 @default.
- W4287202213 hasConcept C111030470 @default.
- W4287202213 hasConcept C11413529 @default.
- W4287202213 hasConcept C119857082 @default.
- W4287202213 hasConcept C121332964 @default.
- W4287202213 hasConcept C126255220 @default.
- W4287202213 hasConcept C131675550 @default.
- W4287202213 hasConcept C137836250 @default.
- W4287202213 hasConcept C154945302 @default.
- W4287202213 hasConcept C163716315 @default.
- W4287202213 hasConcept C2778049539 @default.
- W4287202213 hasConcept C33923547 @default.
- W4287202213 hasConcept C41008148 @default.
- W4287202213 hasConcept C48044578 @default.
- W4287202213 hasConcept C50644808 @default.
- W4287202213 hasConcept C61326573 @default.
- W4287202213 hasConcept C62520636 @default.
- W4287202213 hasConcept C77088390 @default.
- W4287202213 hasConceptScore W4287202213C108583219 @default.
- W4287202213 hasConceptScore W4287202213C111030470 @default.
- W4287202213 hasConceptScore W4287202213C11413529 @default.
- W4287202213 hasConceptScore W4287202213C119857082 @default.
- W4287202213 hasConceptScore W4287202213C121332964 @default.
- W4287202213 hasConceptScore W4287202213C126255220 @default.
- W4287202213 hasConceptScore W4287202213C131675550 @default.
- W4287202213 hasConceptScore W4287202213C137836250 @default.
- W4287202213 hasConceptScore W4287202213C154945302 @default.
- W4287202213 hasConceptScore W4287202213C163716315 @default.
- W4287202213 hasConceptScore W4287202213C2778049539 @default.
- W4287202213 hasConceptScore W4287202213C33923547 @default.
- W4287202213 hasConceptScore W4287202213C41008148 @default.
- W4287202213 hasConceptScore W4287202213C48044578 @default.
- W4287202213 hasConceptScore W4287202213C50644808 @default.
- W4287202213 hasConceptScore W4287202213C61326573 @default.
- W4287202213 hasConceptScore W4287202213C62520636 @default.
- W4287202213 hasConceptScore W4287202213C77088390 @default.
- W4287202213 hasLocation W42872022131 @default.
- W4287202213 hasLocation W42872022132 @default.
- W4287202213 hasOpenAccess W4287202213 @default.
- W4287202213 hasPrimaryLocation W42872022131 @default.
- W4287202213 hasRelatedWork W2950792054 @default.
- W4287202213 hasRelatedWork W3007674363 @default.
- W4287202213 hasRelatedWork W3104422856 @default.
- W4287202213 hasRelatedWork W3134690064 @default.
- W4287202213 hasRelatedWork W4206864338 @default.
- W4287202213 hasRelatedWork W4210726438 @default.
- W4287202213 hasRelatedWork W4237912051 @default.
- W4287202213 hasRelatedWork W4287752080 @default.
- W4287202213 hasRelatedWork W4292081304 @default.
- W4287202213 hasRelatedWork W4380627621 @default.
- W4287202213 isParatext "false" @default.
- W4287202213 isRetracted "false" @default.
- W4287202213 workType "article" @default.