Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034852262> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3034852262 endingPage "4712" @default.
- W3034852262 startingPage "4702" @default.
- W3034852262 abstract "The combination of inducing point methods with stochastic variational inference has enabled approximate Gaussian Process (GP) inference on large datasets. Unfortunately, the resulting predictive distributions often exhibit substantially underestimated uncertainties. Notably, in the regression case the predictive variance is typically dominated by observation noise, yielding uncertainty estimates that make little use of the input-dependent function uncertainty that makes GP priors attractive. In this work we propose two simple methods for scalable GP regression that address this issue and thus yield substantially improved predictive uncertainties. The first applies variational inference to FITC (Fully Independent Training Conditional; Snelson et.~al.~2006). The second bypasses posterior approximations and instead directly targets the posterior predictive distribution. In an extensive empirical comparison with a number of alternative methods for scalable GP regression, we find that the resulting predictive distributions exhibit significantly better calibrated uncertainties and higher log likelihoods--often by as much as half a nat per datapoint." @default.
- W3034852262 created "2020-06-19" @default.
- W3034852262 creator A5054350362 @default.
- W3034852262 creator A5065203625 @default.
- W3034852262 creator A5072585411 @default.
- W3034852262 date "2020-07-12" @default.
- W3034852262 modified "2023-09-26" @default.
- W3034852262 title "Parametric Gaussian Process Regressors" @default.
- W3034852262 hasPublicationYear "2020" @default.
- W3034852262 type Work @default.
- W3034852262 sameAs 3034852262 @default.
- W3034852262 citedByCount "14" @default.
- W3034852262 countsByYear W30348522622019 @default.
- W3034852262 countsByYear W30348522622020 @default.
- W3034852262 countsByYear W30348522622021 @default.
- W3034852262 crossrefType "proceedings-article" @default.
- W3034852262 hasAuthorship W3034852262A5054350362 @default.
- W3034852262 hasAuthorship W3034852262A5065203625 @default.
- W3034852262 hasAuthorship W3034852262A5072585411 @default.
- W3034852262 hasConcept C105795698 @default.
- W3034852262 hasConcept C107673813 @default.
- W3034852262 hasConcept C11413529 @default.
- W3034852262 hasConcept C117251300 @default.
- W3034852262 hasConcept C119857082 @default.
- W3034852262 hasConcept C121332964 @default.
- W3034852262 hasConcept C154945302 @default.
- W3034852262 hasConcept C160234255 @default.
- W3034852262 hasConcept C162376815 @default.
- W3034852262 hasConcept C163716315 @default.
- W3034852262 hasConcept C177769412 @default.
- W3034852262 hasConcept C2776214188 @default.
- W3034852262 hasConcept C32230216 @default.
- W3034852262 hasConcept C33923547 @default.
- W3034852262 hasConcept C37903108 @default.
- W3034852262 hasConcept C41008148 @default.
- W3034852262 hasConcept C57830394 @default.
- W3034852262 hasConcept C61326573 @default.
- W3034852262 hasConcept C62520636 @default.
- W3034852262 hasConcept C83247935 @default.
- W3034852262 hasConcept C83546350 @default.
- W3034852262 hasConcept C917703 @default.
- W3034852262 hasConceptScore W3034852262C105795698 @default.
- W3034852262 hasConceptScore W3034852262C107673813 @default.
- W3034852262 hasConceptScore W3034852262C11413529 @default.
- W3034852262 hasConceptScore W3034852262C117251300 @default.
- W3034852262 hasConceptScore W3034852262C119857082 @default.
- W3034852262 hasConceptScore W3034852262C121332964 @default.
- W3034852262 hasConceptScore W3034852262C154945302 @default.
- W3034852262 hasConceptScore W3034852262C160234255 @default.
- W3034852262 hasConceptScore W3034852262C162376815 @default.
- W3034852262 hasConceptScore W3034852262C163716315 @default.
- W3034852262 hasConceptScore W3034852262C177769412 @default.
- W3034852262 hasConceptScore W3034852262C2776214188 @default.
- W3034852262 hasConceptScore W3034852262C32230216 @default.
- W3034852262 hasConceptScore W3034852262C33923547 @default.
- W3034852262 hasConceptScore W3034852262C37903108 @default.
- W3034852262 hasConceptScore W3034852262C41008148 @default.
- W3034852262 hasConceptScore W3034852262C57830394 @default.
- W3034852262 hasConceptScore W3034852262C61326573 @default.
- W3034852262 hasConceptScore W3034852262C62520636 @default.
- W3034852262 hasConceptScore W3034852262C83247935 @default.
- W3034852262 hasConceptScore W3034852262C83546350 @default.
- W3034852262 hasConceptScore W3034852262C917703 @default.
- W3034852262 hasLocation W30348522621 @default.
- W3034852262 hasOpenAccess W3034852262 @default.
- W3034852262 hasPrimaryLocation W30348522621 @default.
- W3034852262 hasRelatedWork W137285897 @default.
- W3034852262 hasRelatedWork W1502922572 @default.
- W3034852262 hasRelatedWork W1533660737 @default.
- W3034852262 hasRelatedWork W1571870753 @default.
- W3034852262 hasRelatedWork W1663973292 @default.
- W3034852262 hasRelatedWork W1702387805 @default.
- W3034852262 hasRelatedWork W1746819321 @default.
- W3034852262 hasRelatedWork W1777124189 @default.
- W3034852262 hasRelatedWork W1959608418 @default.
- W3034852262 hasRelatedWork W1973310094 @default.
- W3034852262 hasRelatedWork W2099768828 @default.
- W3034852262 hasRelatedWork W2166851633 @default.
- W3034852262 hasRelatedWork W2546173126 @default.
- W3034852262 hasRelatedWork W2963190151 @default.
- W3034852262 hasRelatedWork W2963238274 @default.
- W3034852262 hasRelatedWork W2963566966 @default.
- W3034852262 hasRelatedWork W2964121744 @default.
- W3034852262 hasRelatedWork W2964135722 @default.
- W3034852262 hasRelatedWork W2970971581 @default.
- W3034852262 hasRelatedWork W3101380508 @default.
- W3034852262 hasVolume "1" @default.
- W3034852262 isParatext "false" @default.
- W3034852262 isRetracted "false" @default.
- W3034852262 magId "3034852262" @default.
- W3034852262 workType "article" @default.