Matches in SemOpenAlex for { <https://semopenalex.org/work/W2607746587> ?p ?o ?g. }
- W2607746587 endingPage "1018" @default.
- W2607746587 startingPage "991" @default.
- W2607746587 abstract "Gaussian process (GP) models have become popular for approximating and exploring nonlinear systems using scarce input/output samples and prior hypotheses done through mean and covariance functions. While it is common to make stationarity assumptions and use variance-based criteria for exploration, in realistic cases it is not rare that systems under study exhibit a heterogeneous behavior depending on regions of the parameter space. We consider a class of problems where high variations occur along unknown noncanonical directions and we tackle the problem of accommodating nonstationarity from two angles. First we define a novel class of covariances (WaMI-GP) that simultaneously generalizes kernels of multiple index and of tensorized warped GPs, and second, we introduce derivative-based sampling criteria dedicated to the exploration of high-variation regions. The novel GP class is investigated through both mathematical analysis and numerical experiments, and it is shown that it allows encoding much expressiveness while keeping the number of parameters to be inferred moderate. Criteria and models are compared on a mechanical test case from safety studies conducted by IRSN. On this application some of the proposed criteria outperform usual variance-based criteria in the case of a stationary GP model; however, variance-based criteria with WaMI-GP perform even better. Our method is also compared with the treed Gaussian processes (TGP) on this application and on a NASA test case. In the IRSN application, WaMI-GP dominates TGP in static and sequential settings. In the NASA application, while TGP clearly dominates in the static case, for small designs it is outperformed by WaMI-GP in the sequential setup." @default.
- W2607746587 created "2017-05-05" @default.
- W2607746587 creator A5016462835 @default.
- W2607746587 creator A5041432055 @default.
- W2607746587 creator A5049418200 @default.
- W2607746587 creator A5073016700 @default.
- W2607746587 date "2018-01-01" @default.
- W2607746587 modified "2023-09-25" @default.
- W2607746587 title "Warped Gaussian Processes and Derivative-Based Sequential Designs for Functions with Heterogeneous Variations" @default.
- W2607746587 cites W1510052597 @default.
- W2607746587 cites W1758903565 @default.
- W2607746587 cites W1840389249 @default.
- W2607746587 cites W1914588449 @default.
- W2607746587 cites W1969513389 @default.
- W2607746587 cites W1972655542 @default.
- W2607746587 cites W1978156694 @default.
- W2607746587 cites W1986454681 @default.
- W2607746587 cites W2007676551 @default.
- W2607746587 cites W2016208159 @default.
- W2607746587 cites W2042054333 @default.
- W2607746587 cites W2043653481 @default.
- W2607746587 cites W2050497240 @default.
- W2607746587 cites W2092271904 @default.
- W2607746587 cites W2133118715 @default.
- W2607746587 cites W2135892144 @default.
- W2607746587 cites W2151479892 @default.
- W2607746587 cites W2166566250 @default.
- W2607746587 cites W2171993497 @default.
- W2607746587 cites W2195861446 @default.
- W2607746587 cites W2314144375 @default.
- W2607746587 cites W2592279581 @default.
- W2607746587 cites W2962731272 @default.
- W2607746587 cites W3101730079 @default.
- W2607746587 cites W3196808556 @default.
- W2607746587 cites W4237450968 @default.
- W2607746587 doi "https://doi.org/10.1137/17m1129179" @default.
- W2607746587 hasPublicationYear "2018" @default.
- W2607746587 type Work @default.
- W2607746587 sameAs 2607746587 @default.
- W2607746587 citedByCount "17" @default.
- W2607746587 countsByYear W26077465872017 @default.
- W2607746587 countsByYear W26077465872018 @default.
- W2607746587 countsByYear W26077465872019 @default.
- W2607746587 countsByYear W26077465872020 @default.
- W2607746587 countsByYear W26077465872021 @default.
- W2607746587 countsByYear W26077465872023 @default.
- W2607746587 crossrefType "journal-article" @default.
- W2607746587 hasAuthorship W2607746587A5016462835 @default.
- W2607746587 hasAuthorship W2607746587A5041432055 @default.
- W2607746587 hasAuthorship W2607746587A5049418200 @default.
- W2607746587 hasAuthorship W2607746587A5073016700 @default.
- W2607746587 hasBestOaLocation W26077465872 @default.
- W2607746587 hasConcept C105795698 @default.
- W2607746587 hasConcept C106159729 @default.
- W2607746587 hasConcept C111771559 @default.
- W2607746587 hasConcept C11413529 @default.
- W2607746587 hasConcept C121332964 @default.
- W2607746587 hasConcept C121955636 @default.
- W2607746587 hasConcept C126255220 @default.
- W2607746587 hasConcept C144133560 @default.
- W2607746587 hasConcept C154945302 @default.
- W2607746587 hasConcept C158622935 @default.
- W2607746587 hasConcept C162324750 @default.
- W2607746587 hasConcept C163716315 @default.
- W2607746587 hasConcept C178650346 @default.
- W2607746587 hasConcept C196083921 @default.
- W2607746587 hasConcept C2777212361 @default.
- W2607746587 hasConcept C2778334786 @default.
- W2607746587 hasConcept C28826006 @default.
- W2607746587 hasConcept C33923547 @default.
- W2607746587 hasConcept C41008148 @default.
- W2607746587 hasConcept C44870925 @default.
- W2607746587 hasConcept C61326573 @default.
- W2607746587 hasConcept C62520636 @default.
- W2607746587 hasConceptScore W2607746587C105795698 @default.
- W2607746587 hasConceptScore W2607746587C106159729 @default.
- W2607746587 hasConceptScore W2607746587C111771559 @default.
- W2607746587 hasConceptScore W2607746587C11413529 @default.
- W2607746587 hasConceptScore W2607746587C121332964 @default.
- W2607746587 hasConceptScore W2607746587C121955636 @default.
- W2607746587 hasConceptScore W2607746587C126255220 @default.
- W2607746587 hasConceptScore W2607746587C144133560 @default.
- W2607746587 hasConceptScore W2607746587C154945302 @default.
- W2607746587 hasConceptScore W2607746587C158622935 @default.
- W2607746587 hasConceptScore W2607746587C162324750 @default.
- W2607746587 hasConceptScore W2607746587C163716315 @default.
- W2607746587 hasConceptScore W2607746587C178650346 @default.
- W2607746587 hasConceptScore W2607746587C196083921 @default.
- W2607746587 hasConceptScore W2607746587C2777212361 @default.
- W2607746587 hasConceptScore W2607746587C2778334786 @default.
- W2607746587 hasConceptScore W2607746587C28826006 @default.
- W2607746587 hasConceptScore W2607746587C33923547 @default.
- W2607746587 hasConceptScore W2607746587C41008148 @default.
- W2607746587 hasConceptScore W2607746587C44870925 @default.
- W2607746587 hasConceptScore W2607746587C61326573 @default.
- W2607746587 hasConceptScore W2607746587C62520636 @default.
- W2607746587 hasIssue "3" @default.
- W2607746587 hasLocation W26077465871 @default.