Matches in SemOpenAlex for { <https://semopenalex.org/work/W2997782896> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2997782896 endingPage "6004" @default.
- W2997782896 startingPage "5997" @default.
- W2997782896 abstract "This paper presents a variational Bayesian kernel selection (VBKS) algorithm for sparse Gaussian process regression (SGPR) models. In contrast to existing GP kernel selection algorithms that aim to select only one kernel with the highest model evidence, our VBKS algorithm considers the kernel as a random variable and learns its belief from data such that the uncertainty of the kernel can be interpreted and exploited to avoid overconfident GP predictions. To achieve this, we represent the probabilistic kernel as an additional variational variable in a variational inference (VI) framework for SGPR models where its posterior belief is learned together with that of the other variational variables (i.e., inducing variables and kernel hyperparameters). In particular, we transform the discrete kernel belief into a continuous parametric distribution via reparameterization in order to apply VI. Though it is computationally challenging to jointly optimize a large number of hyperparameters due to many kernels being evaluated simultaneously by our VBKS algorithm, we show that the variational lower bound of the log-marginal likelihood can be decomposed into an additive form such that each additive term depends only on a disjoint subset of the variational variables and can thus be optimized independently. Stochastic optimization is then used to maximize the variational lower bound by iteratively improving the variational approximation of the exact posterior belief via stochastic gradient ascent, which incurs constant time per iteration and hence scales to big data. We empirically evaluate the performance of our VBKS algorithm on synthetic and massive real-world datasets." @default.
- W2997782896 created "2020-01-10" @default.
- W2997782896 creator A5007250648 @default.
- W2997782896 creator A5010479652 @default.
- W2997782896 creator A5030304400 @default.
- W2997782896 creator A5058034592 @default.
- W2997782896 date "2020-04-03" @default.
- W2997782896 modified "2023-09-25" @default.
- W2997782896 title "Scalable Variational Bayesian Kernel Selection for Sparse Gaussian Process Regression" @default.
- W2997782896 doi "https://doi.org/10.1609/aaai.v34i04.6061" @default.
- W2997782896 hasPublicationYear "2020" @default.
- W2997782896 type Work @default.
- W2997782896 sameAs 2997782896 @default.
- W2997782896 citedByCount "15" @default.
- W2997782896 countsByYear W29977828962020 @default.
- W2997782896 countsByYear W29977828962021 @default.
- W2997782896 countsByYear W29977828962022 @default.
- W2997782896 countsByYear W29977828962023 @default.
- W2997782896 crossrefType "journal-article" @default.
- W2997782896 hasAuthorship W2997782896A5007250648 @default.
- W2997782896 hasAuthorship W2997782896A5010479652 @default.
- W2997782896 hasAuthorship W2997782896A5030304400 @default.
- W2997782896 hasAuthorship W2997782896A5058034592 @default.
- W2997782896 hasBestOaLocation W29977828961 @default.
- W2997782896 hasConcept C107673813 @default.
- W2997782896 hasConcept C11413529 @default.
- W2997782896 hasConcept C114614502 @default.
- W2997782896 hasConcept C121332964 @default.
- W2997782896 hasConcept C122280245 @default.
- W2997782896 hasConcept C12267149 @default.
- W2997782896 hasConcept C126255220 @default.
- W2997782896 hasConcept C154945302 @default.
- W2997782896 hasConcept C163716315 @default.
- W2997782896 hasConcept C195699287 @default.
- W2997782896 hasConcept C28826006 @default.
- W2997782896 hasConcept C33923547 @default.
- W2997782896 hasConcept C41008148 @default.
- W2997782896 hasConcept C61326573 @default.
- W2997782896 hasConcept C62520636 @default.
- W2997782896 hasConcept C74193536 @default.
- W2997782896 hasConcept C8642999 @default.
- W2997782896 hasConcept C95923904 @default.
- W2997782896 hasConceptScore W2997782896C107673813 @default.
- W2997782896 hasConceptScore W2997782896C11413529 @default.
- W2997782896 hasConceptScore W2997782896C114614502 @default.
- W2997782896 hasConceptScore W2997782896C121332964 @default.
- W2997782896 hasConceptScore W2997782896C122280245 @default.
- W2997782896 hasConceptScore W2997782896C12267149 @default.
- W2997782896 hasConceptScore W2997782896C126255220 @default.
- W2997782896 hasConceptScore W2997782896C154945302 @default.
- W2997782896 hasConceptScore W2997782896C163716315 @default.
- W2997782896 hasConceptScore W2997782896C195699287 @default.
- W2997782896 hasConceptScore W2997782896C28826006 @default.
- W2997782896 hasConceptScore W2997782896C33923547 @default.
- W2997782896 hasConceptScore W2997782896C41008148 @default.
- W2997782896 hasConceptScore W2997782896C61326573 @default.
- W2997782896 hasConceptScore W2997782896C62520636 @default.
- W2997782896 hasConceptScore W2997782896C74193536 @default.
- W2997782896 hasConceptScore W2997782896C8642999 @default.
- W2997782896 hasConceptScore W2997782896C95923904 @default.
- W2997782896 hasIssue "04" @default.
- W2997782896 hasLocation W29977828961 @default.
- W2997782896 hasLocation W29977828962 @default.
- W2997782896 hasOpenAccess W2997782896 @default.
- W2997782896 hasPrimaryLocation W29977828961 @default.
- W2997782896 hasRelatedWork W1558591020 @default.
- W2997782896 hasRelatedWork W2028245348 @default.
- W2997782896 hasRelatedWork W2071570209 @default.
- W2997782896 hasRelatedWork W2141609920 @default.
- W2997782896 hasRelatedWork W2142373740 @default.
- W2997782896 hasRelatedWork W2977967020 @default.
- W2997782896 hasRelatedWork W3034251610 @default.
- W2997782896 hasRelatedWork W3102858373 @default.
- W2997782896 hasRelatedWork W3210899060 @default.
- W2997782896 hasRelatedWork W4284968297 @default.
- W2997782896 hasVolume "34" @default.
- W2997782896 isParatext "false" @default.
- W2997782896 isRetracted "false" @default.
- W2997782896 magId "2997782896" @default.
- W2997782896 workType "article" @default.