Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312526562> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4312526562 endingPage "1231" @default.
- W4312526562 startingPage "1222" @default.
- W4312526562 abstract "Carrying out Bayesian inference over parameters of statistical models is intractable when the likelihood and the prior are non-conjugate. Variational bootstrap provides a way to obtain samples from the posterior distribution over model parameters, where each sample is the solution of a task where the labels are perturbed. For Bayesian linear regression with a Gaussian likelihood, variational bootstrap yields samples from the exact posterior, whereas for nonlinear models with a Gaussian likelihood some guarantees of approaching the true posterior can be established. In this work, we extend variational bootstrap to the Bernoulli likelihood to tackle classification tasks. We use a transformation of the labels which allows us to turn the classification task into a regression one, and then we apply variational bootstrap to obtain samples from an approximate posterior distribution over the parameters of the model. Variational bootstrap allows us to employ advanced gradient optimization techniques which provide fast convergence. We provide experimental evidence that the proposed approach allows us to achieve classification accuracy and uncertainty estimation comparable with MCMC methods at a fraction of the cost." @default.
- W4312526562 created "2023-01-05" @default.
- W4312526562 creator A5009313402 @default.
- W4312526562 creator A5021162375 @default.
- W4312526562 creator A5027711912 @default.
- W4312526562 date "2022-01-01" @default.
- W4312526562 modified "2023-09-30" @default.
- W4312526562 title "Variational Bootstrap for Classification" @default.
- W4312526562 cites W2026915078 @default.
- W4312526562 cites W2086883550 @default.
- W4312526562 cites W2213443318 @default.
- W4312526562 cites W2885453527 @default.
- W4312526562 cites W2931364255 @default.
- W4312526562 cites W3099490698 @default.
- W4312526562 cites W4252684946 @default.
- W4312526562 doi "https://doi.org/10.1016/j.procs.2022.09.178" @default.
- W4312526562 hasPublicationYear "2022" @default.
- W4312526562 type Work @default.
- W4312526562 citedByCount "0" @default.
- W4312526562 crossrefType "journal-article" @default.
- W4312526562 hasAuthorship W4312526562A5009313402 @default.
- W4312526562 hasAuthorship W4312526562A5021162375 @default.
- W4312526562 hasAuthorship W4312526562A5027711912 @default.
- W4312526562 hasBestOaLocation W43125265621 @default.
- W4312526562 hasConcept C107673813 @default.
- W4312526562 hasConcept C11413529 @default.
- W4312526562 hasConcept C121332964 @default.
- W4312526562 hasConcept C126255220 @default.
- W4312526562 hasConcept C154945302 @default.
- W4312526562 hasConcept C160234255 @default.
- W4312526562 hasConcept C162324750 @default.
- W4312526562 hasConcept C163716315 @default.
- W4312526562 hasConcept C26004113 @default.
- W4312526562 hasConcept C2776214188 @default.
- W4312526562 hasConcept C2777303404 @default.
- W4312526562 hasConcept C28826006 @default.
- W4312526562 hasConcept C33923547 @default.
- W4312526562 hasConcept C41008148 @default.
- W4312526562 hasConcept C50522688 @default.
- W4312526562 hasConcept C57830394 @default.
- W4312526562 hasConcept C62520636 @default.
- W4312526562 hasConcept C95923904 @default.
- W4312526562 hasConceptScore W4312526562C107673813 @default.
- W4312526562 hasConceptScore W4312526562C11413529 @default.
- W4312526562 hasConceptScore W4312526562C121332964 @default.
- W4312526562 hasConceptScore W4312526562C126255220 @default.
- W4312526562 hasConceptScore W4312526562C154945302 @default.
- W4312526562 hasConceptScore W4312526562C160234255 @default.
- W4312526562 hasConceptScore W4312526562C162324750 @default.
- W4312526562 hasConceptScore W4312526562C163716315 @default.
- W4312526562 hasConceptScore W4312526562C26004113 @default.
- W4312526562 hasConceptScore W4312526562C2776214188 @default.
- W4312526562 hasConceptScore W4312526562C2777303404 @default.
- W4312526562 hasConceptScore W4312526562C28826006 @default.
- W4312526562 hasConceptScore W4312526562C33923547 @default.
- W4312526562 hasConceptScore W4312526562C41008148 @default.
- W4312526562 hasConceptScore W4312526562C50522688 @default.
- W4312526562 hasConceptScore W4312526562C57830394 @default.
- W4312526562 hasConceptScore W4312526562C62520636 @default.
- W4312526562 hasConceptScore W4312526562C95923904 @default.
- W4312526562 hasLocation W43125265621 @default.
- W4312526562 hasOpenAccess W4312526562 @default.
- W4312526562 hasPrimaryLocation W43125265621 @default.
- W4312526562 hasRelatedWork W2110811157 @default.
- W4312526562 hasRelatedWork W3126140132 @default.
- W4312526562 hasRelatedWork W3133492393 @default.
- W4312526562 hasRelatedWork W3168765527 @default.
- W4312526562 hasRelatedWork W3212010304 @default.
- W4312526562 hasRelatedWork W4225820491 @default.
- W4312526562 hasRelatedWork W4246698572 @default.
- W4312526562 hasRelatedWork W4306878334 @default.
- W4312526562 hasRelatedWork W4384648042 @default.
- W4312526562 hasRelatedWork W2184215046 @default.
- W4312526562 hasVolume "207" @default.
- W4312526562 isParatext "false" @default.
- W4312526562 isRetracted "false" @default.
- W4312526562 workType "article" @default.