Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037321753> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W3037321753 endingPage "4572" @default.
- W3037321753 startingPage "4563" @default.
- W3037321753 abstract "Gradient-based approximate inference methods, such as Stein variational gradient descent (SVGD), provide simple and general-purpose inference engines for differentiable continuous distributions. However, existing forms of SVGD cannot be directly applied to discrete distributions. In this work, we fill this gap by proposing a simple yet general framework that transforms discrete distributions to equivalent piecewise continuous distributions, on which the gradient-free SVGD is applied to perform efficient approximate inference. The empirical results show that our method outperforms traditional algorithms such as Gibbs sampling and discontinuous Hamiltonian Monte Carlo on various challenging benchmarks of discrete graphical models. We demonstrate that our method provides a promising tool for learning ensembles of binarized neural network (BNN), outperforming other widely used ensemble methods on learning binarized AlexNet on CIFAR-10 dataset. In addition, such transform can be straightforwardly employed in gradient-free kernelized Stein discrepancy to perform goodness-of-fit (GOF) test on discrete distributions. Our proposed method outperforms existing GOF test methods for intractable discrete distributions." @default.
- W3037321753 created "2020-07-02" @default.
- W3037321753 creator A5024067284 @default.
- W3037321753 creator A5047373240 @default.
- W3037321753 creator A5052740608 @default.
- W3037321753 creator A5073124436 @default.
- W3037321753 creator A5073424108 @default.
- W3037321753 creator A5082736347 @default.
- W3037321753 date "2020-06-03" @default.
- W3037321753 modified "2023-09-29" @default.
- W3037321753 title "Stein Variational Inference for Discrete Distributions" @default.
- W3037321753 hasPublicationYear "2020" @default.
- W3037321753 type Work @default.
- W3037321753 sameAs 3037321753 @default.
- W3037321753 citedByCount "5" @default.
- W3037321753 countsByYear W30373217532020 @default.
- W3037321753 countsByYear W30373217532021 @default.
- W3037321753 crossrefType "proceedings-article" @default.
- W3037321753 hasAuthorship W3037321753A5024067284 @default.
- W3037321753 hasAuthorship W3037321753A5047373240 @default.
- W3037321753 hasAuthorship W3037321753A5052740608 @default.
- W3037321753 hasAuthorship W3037321753A5073124436 @default.
- W3037321753 hasAuthorship W3037321753A5073424108 @default.
- W3037321753 hasAuthorship W3037321753A5082736347 @default.
- W3037321753 hasConcept C11413529 @default.
- W3037321753 hasConcept C134306372 @default.
- W3037321753 hasConcept C153258448 @default.
- W3037321753 hasConcept C154945302 @default.
- W3037321753 hasConcept C164660894 @default.
- W3037321753 hasConcept C202615002 @default.
- W3037321753 hasConcept C2776214188 @default.
- W3037321753 hasConcept C28826006 @default.
- W3037321753 hasConcept C33923547 @default.
- W3037321753 hasConcept C41008148 @default.
- W3037321753 hasConcept C50644808 @default.
- W3037321753 hasConceptScore W3037321753C11413529 @default.
- W3037321753 hasConceptScore W3037321753C134306372 @default.
- W3037321753 hasConceptScore W3037321753C153258448 @default.
- W3037321753 hasConceptScore W3037321753C154945302 @default.
- W3037321753 hasConceptScore W3037321753C164660894 @default.
- W3037321753 hasConceptScore W3037321753C202615002 @default.
- W3037321753 hasConceptScore W3037321753C2776214188 @default.
- W3037321753 hasConceptScore W3037321753C28826006 @default.
- W3037321753 hasConceptScore W3037321753C33923547 @default.
- W3037321753 hasConceptScore W3037321753C41008148 @default.
- W3037321753 hasConceptScore W3037321753C50644808 @default.
- W3037321753 hasLocation W30373217531 @default.
- W3037321753 hasOpenAccess W3037321753 @default.
- W3037321753 hasPrimaryLocation W30373217531 @default.
- W3037321753 hasRelatedWork W1512450818 @default.
- W3037321753 hasRelatedWork W1533901278 @default.
- W3037321753 hasRelatedWork W1534145347 @default.
- W3037321753 hasRelatedWork W1843468135 @default.
- W3037321753 hasRelatedWork W2123348968 @default.
- W3037321753 hasRelatedWork W2144518280 @default.
- W3037321753 hasRelatedWork W2156417670 @default.
- W3037321753 hasRelatedWork W2174412056 @default.
- W3037321753 hasRelatedWork W2462157830 @default.
- W3037321753 hasRelatedWork W2754804723 @default.
- W3037321753 hasRelatedWork W2888855694 @default.
- W3037321753 hasRelatedWork W2964141597 @default.
- W3037321753 hasRelatedWork W2979719808 @default.
- W3037321753 hasRelatedWork W2980249749 @default.
- W3037321753 hasRelatedWork W2989695133 @default.
- W3037321753 hasRelatedWork W3007508432 @default.
- W3037321753 hasRelatedWork W3022854535 @default.
- W3037321753 hasRelatedWork W3031275541 @default.
- W3037321753 hasRelatedWork W3039869504 @default.
- W3037321753 hasRelatedWork W3103250059 @default.
- W3037321753 isParatext "false" @default.
- W3037321753 isRetracted "false" @default.
- W3037321753 magId "3037321753" @default.
- W3037321753 workType "article" @default.