Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308505103> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4308505103 abstract "The kernel function and its hyperparameters are the central model selection choice in a Gaussian proces (Rasmussen and Williams, 2006). Typically, the hyperparameters of the kernel are chosen by maximising the marginal likelihood, an approach known as Type-II maximum likelihood (ML-II). However, ML-II does not account for hyperparameter uncertainty, and it is well-known that this can lead to severely biased estimates and an underestimation of predictive uncertainty. While there are several works which employ a fully Bayesian characterisation of GPs, relatively few propose such approaches for the sparse GPs paradigm. In this work we propose an algorithm for sparse Gaussian process regression which leverages MCMC to sample from the hyperparameter posterior within the variational inducing point framework of Titsias (2009). This work is closely related to Hensman et al. (2015b) but side-steps the need to sample the inducing points, thereby significantly improving sampling efficiency in the Gaussian likelihood case. We compare this scheme against natural baselines in literature along with stochastic variational GPs (SVGPs) along with an extensive computational analysis." @default.
- W4308505103 created "2022-11-12" @default.
- W4308505103 creator A5022158131 @default.
- W4308505103 creator A5043989930 @default.
- W4308505103 creator A5061327791 @default.
- W4308505103 creator A5070699450 @default.
- W4308505103 date "2022-11-04" @default.
- W4308505103 modified "2023-09-27" @default.
- W4308505103 title "Sparse Gaussian Process Hyperparameters: Optimize or Integrate?" @default.
- W4308505103 doi "https://doi.org/10.48550/arxiv.2211.02476" @default.
- W4308505103 hasPublicationYear "2022" @default.
- W4308505103 type Work @default.
- W4308505103 citedByCount "0" @default.
- W4308505103 crossrefType "posted-content" @default.
- W4308505103 hasAuthorship W4308505103A5022158131 @default.
- W4308505103 hasAuthorship W4308505103A5043989930 @default.
- W4308505103 hasAuthorship W4308505103A5061327791 @default.
- W4308505103 hasAuthorship W4308505103A5070699450 @default.
- W4308505103 hasBestOaLocation W43085051031 @default.
- W4308505103 hasConcept C10485038 @default.
- W4308505103 hasConcept C107673813 @default.
- W4308505103 hasConcept C11413529 @default.
- W4308505103 hasConcept C114614502 @default.
- W4308505103 hasConcept C119857082 @default.
- W4308505103 hasConcept C121332964 @default.
- W4308505103 hasConcept C12267149 @default.
- W4308505103 hasConcept C126255220 @default.
- W4308505103 hasConcept C154945302 @default.
- W4308505103 hasConcept C163716315 @default.
- W4308505103 hasConcept C33923547 @default.
- W4308505103 hasConcept C41008148 @default.
- W4308505103 hasConcept C61326573 @default.
- W4308505103 hasConcept C62520636 @default.
- W4308505103 hasConcept C74193536 @default.
- W4308505103 hasConcept C8642999 @default.
- W4308505103 hasConcept C95923904 @default.
- W4308505103 hasConceptScore W4308505103C10485038 @default.
- W4308505103 hasConceptScore W4308505103C107673813 @default.
- W4308505103 hasConceptScore W4308505103C11413529 @default.
- W4308505103 hasConceptScore W4308505103C114614502 @default.
- W4308505103 hasConceptScore W4308505103C119857082 @default.
- W4308505103 hasConceptScore W4308505103C121332964 @default.
- W4308505103 hasConceptScore W4308505103C12267149 @default.
- W4308505103 hasConceptScore W4308505103C126255220 @default.
- W4308505103 hasConceptScore W4308505103C154945302 @default.
- W4308505103 hasConceptScore W4308505103C163716315 @default.
- W4308505103 hasConceptScore W4308505103C33923547 @default.
- W4308505103 hasConceptScore W4308505103C41008148 @default.
- W4308505103 hasConceptScore W4308505103C61326573 @default.
- W4308505103 hasConceptScore W4308505103C62520636 @default.
- W4308505103 hasConceptScore W4308505103C74193536 @default.
- W4308505103 hasConceptScore W4308505103C8642999 @default.
- W4308505103 hasConceptScore W4308505103C95923904 @default.
- W4308505103 hasLocation W43085051031 @default.
- W4308505103 hasLocation W43085051032 @default.
- W4308505103 hasOpenAccess W4308505103 @default.
- W4308505103 hasPrimaryLocation W43085051031 @default.
- W4308505103 hasRelatedWork W2977967020 @default.
- W4308505103 hasRelatedWork W3199608561 @default.
- W4308505103 hasRelatedWork W4220716427 @default.
- W4308505103 hasRelatedWork W4283697347 @default.
- W4308505103 hasRelatedWork W4295309597 @default.
- W4308505103 hasRelatedWork W4298144215 @default.
- W4308505103 hasRelatedWork W4308505103 @default.
- W4308505103 hasRelatedWork W4323894855 @default.
- W4308505103 hasRelatedWork W4384929195 @default.
- W4308505103 hasRelatedWork W4384932390 @default.
- W4308505103 isParatext "false" @default.
- W4308505103 isRetracted "false" @default.
- W4308505103 workType "article" @default.