Matches in SemOpenAlex for { <https://semopenalex.org/work/W2786312416> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2786312416 abstract "A statistical model is said to be un-normalised when its likelihood function involves an intractable normalising constant. Two popular methods for parameter inference for these models are MC-MLE (Monte Carlo maximum likelihood estimation), and NCE (noise contrastive estimation); both methods rely on simulating artificial data-points to approximate the normalising constant. While the asymptotics of MC-MLE have been established under general hypotheses (Geyer, 1994), this is not so for NCE. We establish consistency and asymptotic normality of NCE estimators under mild assumptions. We compare NCE and MC-MLE under several asymptotic regimes. In particular, we show that, when m goes to infinity while n is fixed (m and n being respectively the number of artificial data-points, and actual data-points), the two estimators are asymptotically equivalent. Conversely, we prove that, when the artificial data-points are IID, and when n goes to infinity while m/n converges to a positive constant, the asymptotic variance of a NCE estimator is always smaller than the asymptotic variance of the corresponding MC-MLE estimator. We illustrate the variance reduction brought by NCE through a numerical study." @default.
- W2786312416 created "2018-02-23" @default.
- W2786312416 creator A5049392160 @default.
- W2786312416 creator A5052203922 @default.
- W2786312416 date "2018-01-31" @default.
- W2786312416 modified "2023-09-24" @default.
- W2786312416 title "Noise contrastive estimation: asymptotics, comparison with MC-MLE" @default.
- W2786312416 cites W189596042 @default.
- W2786312416 hasPublicationYear "2018" @default.
- W2786312416 type Work @default.
- W2786312416 sameAs 2786312416 @default.
- W2786312416 citedByCount "3" @default.
- W2786312416 countsByYear W27863124162018 @default.
- W2786312416 countsByYear W27863124162020 @default.
- W2786312416 crossrefType "posted-content" @default.
- W2786312416 hasAuthorship W2786312416A5049392160 @default.
- W2786312416 hasAuthorship W2786312416A5052203922 @default.
- W2786312416 hasConcept C100906024 @default.
- W2786312416 hasConcept C105795698 @default.
- W2786312416 hasConcept C118615104 @default.
- W2786312416 hasConcept C134261354 @default.
- W2786312416 hasConcept C134306372 @default.
- W2786312416 hasConcept C14036430 @default.
- W2786312416 hasConcept C185429906 @default.
- W2786312416 hasConcept C199360897 @default.
- W2786312416 hasConcept C2776436953 @default.
- W2786312416 hasConcept C2777027219 @default.
- W2786312416 hasConcept C28826006 @default.
- W2786312416 hasConcept C33643355 @default.
- W2786312416 hasConcept C33923547 @default.
- W2786312416 hasConcept C41008148 @default.
- W2786312416 hasConcept C65778772 @default.
- W2786312416 hasConcept C7321624 @default.
- W2786312416 hasConcept C78458016 @default.
- W2786312416 hasConcept C86803240 @default.
- W2786312416 hasConcept C91025261 @default.
- W2786312416 hasConcept C971699 @default.
- W2786312416 hasConceptScore W2786312416C100906024 @default.
- W2786312416 hasConceptScore W2786312416C105795698 @default.
- W2786312416 hasConceptScore W2786312416C118615104 @default.
- W2786312416 hasConceptScore W2786312416C134261354 @default.
- W2786312416 hasConceptScore W2786312416C134306372 @default.
- W2786312416 hasConceptScore W2786312416C14036430 @default.
- W2786312416 hasConceptScore W2786312416C185429906 @default.
- W2786312416 hasConceptScore W2786312416C199360897 @default.
- W2786312416 hasConceptScore W2786312416C2776436953 @default.
- W2786312416 hasConceptScore W2786312416C2777027219 @default.
- W2786312416 hasConceptScore W2786312416C28826006 @default.
- W2786312416 hasConceptScore W2786312416C33643355 @default.
- W2786312416 hasConceptScore W2786312416C33923547 @default.
- W2786312416 hasConceptScore W2786312416C41008148 @default.
- W2786312416 hasConceptScore W2786312416C65778772 @default.
- W2786312416 hasConceptScore W2786312416C7321624 @default.
- W2786312416 hasConceptScore W2786312416C78458016 @default.
- W2786312416 hasConceptScore W2786312416C86803240 @default.
- W2786312416 hasConceptScore W2786312416C91025261 @default.
- W2786312416 hasConceptScore W2786312416C971699 @default.
- W2786312416 hasLocation W27863124161 @default.
- W2786312416 hasOpenAccess W2786312416 @default.
- W2786312416 hasPrimaryLocation W27863124161 @default.
- W2786312416 hasRelatedWork W1915631879 @default.
- W2786312416 hasRelatedWork W2013662782 @default.
- W2786312416 hasRelatedWork W2020618776 @default.
- W2786312416 hasRelatedWork W2024499973 @default.
- W2786312416 hasRelatedWork W2148719904 @default.
- W2786312416 hasRelatedWork W2258412789 @default.
- W2786312416 hasRelatedWork W2439581045 @default.
- W2786312416 hasRelatedWork W2606772898 @default.
- W2786312416 hasRelatedWork W2608844860 @default.
- W2786312416 hasRelatedWork W2907426184 @default.
- W2786312416 hasRelatedWork W2951093609 @default.
- W2786312416 hasRelatedWork W2953160415 @default.
- W2786312416 hasRelatedWork W2963182765 @default.
- W2786312416 hasRelatedWork W3024107719 @default.
- W2786312416 hasRelatedWork W3026313128 @default.
- W2786312416 hasRelatedWork W3101586182 @default.
- W2786312416 hasRelatedWork W3122427702 @default.
- W2786312416 hasRelatedWork W3181135704 @default.
- W2786312416 hasRelatedWork W3204181636 @default.
- W2786312416 hasRelatedWork W2137193534 @default.
- W2786312416 isParatext "false" @default.
- W2786312416 isRetracted "false" @default.
- W2786312416 magId "2786312416" @default.
- W2786312416 workType "article" @default.