Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912488555> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2912488555 endingPage "190" @default.
- W2912488555 startingPage "180" @default.
- W2912488555 abstract "Abstract Expectation propagation (EP) is a widely used deterministic approximate inference algorithm in Bayesian machine learning. Traditional EP approximates an intractable posterior distribution through a set of local approximations which are updated iteratively. In this paper, we propose a generalized version of EP called generalized EP (GEP), which is a new method based on the minimization of KL divergence for approximate inference. However, when the variance of the gradient is large, the algorithm may need a long time to converge. We use control variates and develop a variance reduced version of this method called GEP-CV. We evaluate our approach on Bayesian logistic regression, which provides faster convergence and better performance than other state-of-the-art approaches." @default.
- W2912488555 created "2019-02-21" @default.
- W2912488555 creator A5047846625 @default.
- W2912488555 creator A5089489882 @default.
- W2912488555 date "2019-04-01" @default.
- W2912488555 modified "2023-09-24" @default.
- W2912488555 title "Generalizing expectation propagation with mixtures of exponential family distributions and an application to Bayesian logistic regression" @default.
- W2912488555 cites W1972657624 @default.
- W2912488555 cites W1976070817 @default.
- W2912488555 cites W1994616650 @default.
- W2912488555 cites W2045798132 @default.
- W2912488555 cites W2112786982 @default.
- W2912488555 cites W2129259757 @default.
- W2912488555 cites W2130395838 @default.
- W2912488555 cites W2133627190 @default.
- W2912488555 cites W2141250485 @default.
- W2912488555 cites W2747102432 @default.
- W2912488555 cites W2963907691 @default.
- W2912488555 cites W4245929652 @default.
- W2912488555 doi "https://doi.org/10.1016/j.neucom.2019.01.065" @default.
- W2912488555 hasPublicationYear "2019" @default.
- W2912488555 type Work @default.
- W2912488555 sameAs 2912488555 @default.
- W2912488555 citedByCount "3" @default.
- W2912488555 countsByYear W29124885552020 @default.
- W2912488555 countsByYear W29124885552021 @default.
- W2912488555 countsByYear W29124885552022 @default.
- W2912488555 crossrefType "journal-article" @default.
- W2912488555 hasAuthorship W2912488555A5047846625 @default.
- W2912488555 hasAuthorship W2912488555A5089489882 @default.
- W2912488555 hasConcept C105795698 @default.
- W2912488555 hasConcept C107673813 @default.
- W2912488555 hasConcept C134306372 @default.
- W2912488555 hasConcept C149782125 @default.
- W2912488555 hasConcept C151376022 @default.
- W2912488555 hasConcept C151956035 @default.
- W2912488555 hasConcept C154945302 @default.
- W2912488555 hasConcept C33923547 @default.
- W2912488555 hasConcept C41008148 @default.
- W2912488555 hasConcept C55974624 @default.
- W2912488555 hasConcept C60775368 @default.
- W2912488555 hasConcept C83546350 @default.
- W2912488555 hasConceptScore W2912488555C105795698 @default.
- W2912488555 hasConceptScore W2912488555C107673813 @default.
- W2912488555 hasConceptScore W2912488555C134306372 @default.
- W2912488555 hasConceptScore W2912488555C149782125 @default.
- W2912488555 hasConceptScore W2912488555C151376022 @default.
- W2912488555 hasConceptScore W2912488555C151956035 @default.
- W2912488555 hasConceptScore W2912488555C154945302 @default.
- W2912488555 hasConceptScore W2912488555C33923547 @default.
- W2912488555 hasConceptScore W2912488555C41008148 @default.
- W2912488555 hasConceptScore W2912488555C55974624 @default.
- W2912488555 hasConceptScore W2912488555C60775368 @default.
- W2912488555 hasConceptScore W2912488555C83546350 @default.
- W2912488555 hasFunder F4320321001 @default.
- W2912488555 hasLocation W29124885551 @default.
- W2912488555 hasOpenAccess W2912488555 @default.
- W2912488555 hasPrimaryLocation W29124885551 @default.
- W2912488555 hasRelatedWork W1679830183 @default.
- W2912488555 hasRelatedWork W1998025699 @default.
- W2912488555 hasRelatedWork W2028719861 @default.
- W2912488555 hasRelatedWork W2086597262 @default.
- W2912488555 hasRelatedWork W2619715168 @default.
- W2912488555 hasRelatedWork W2905881975 @default.
- W2912488555 hasRelatedWork W2962823242 @default.
- W2912488555 hasRelatedWork W3183939650 @default.
- W2912488555 hasRelatedWork W4210340638 @default.
- W2912488555 hasRelatedWork W4299373414 @default.
- W2912488555 hasVolume "337" @default.
- W2912488555 isParatext "false" @default.
- W2912488555 isRetracted "false" @default.
- W2912488555 magId "2912488555" @default.
- W2912488555 workType "article" @default.