Matches in SemOpenAlex for { <https://semopenalex.org/work/W2794804527> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2794804527 abstract "Gradient-based Monte Carlo sampling algorithms, like Langevin dynamics and Hamiltonian Monte Carlo, are important methods for Bayesian inference. In large-scale settings, full-gradients are not affordable and thus stochastic gradients evaluated on mini-batches are used as a replacement. In order to reduce the high variance of noisy stochastic gradients, Dubey et al. [2016] applied the standard variance reduction technique on stochastic gradient Langevin dynamics and obtained both theoretical and experimental improvements. In this paper, we apply the variance reduction tricks on Hamiltonian Monte Carlo and achieve better theoretical convergence results compared with the variance-reduced Langevin dynamics. Moreover, we apply the symmetric splitting scheme in our variance-reduced Hamiltonian Monte Carlo algorithms to further improve the theoretical results. The experimental results are also consistent with the theoretical results. As our experiment shows, variance-reduced Hamiltonian Monte Carlo demonstrates better performance than variance-reduced Langevin dynamics in Bayesian regression and classification tasks on real-world datasets." @default.
- W2794804527 created "2018-04-06" @default.
- W2794804527 creator A5052883326 @default.
- W2794804527 creator A5060340617 @default.
- W2794804527 creator A5073806117 @default.
- W2794804527 date "2018-03-29" @default.
- W2794804527 modified "2023-09-23" @default.
- W2794804527 title "Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference" @default.
- W2794804527 cites W1545319692 @default.
- W2794804527 cites W1994616650 @default.
- W2794804527 cites W2059448777 @default.
- W2794804527 cites W2107438106 @default.
- W2794804527 cites W2110529144 @default.
- W2794804527 cites W2135482703 @default.
- W2794804527 cites W2144193737 @default.
- W2794804527 cites W2161340280 @default.
- W2794804527 cites W2165652770 @default.
- W2794804527 cites W2167433878 @default.
- W2794804527 cites W2186210550 @default.
- W2794804527 cites W2478027467 @default.
- W2794804527 cites W2549291898 @default.
- W2794804527 cites W2552704617 @default.
- W2794804527 cites W2786446316 @default.
- W2794804527 cites W2948000265 @default.
- W2794804527 cites W2962732346 @default.
- W2794804527 cites W2962851402 @default.
- W2794804527 cites W2963607709 @default.
- W2794804527 cites W2963614065 @default.
- W2794804527 cites W2963965485 @default.
- W2794804527 cites W2965614861 @default.
- W2794804527 cites W2971032006 @default.
- W2794804527 cites W3100981869 @default.
- W2794804527 cites W3401598 @default.
- W2794804527 doi "https://doi.org/10.48550/arxiv.1803.11159" @default.
- W2794804527 hasPublicationYear "2018" @default.
- W2794804527 type Work @default.
- W2794804527 sameAs 2794804527 @default.
- W2794804527 citedByCount "6" @default.
- W2794804527 countsByYear W27948045272017 @default.
- W2794804527 countsByYear W27948045272019 @default.
- W2794804527 countsByYear W27948045272020 @default.
- W2794804527 countsByYear W27948045272021 @default.
- W2794804527 crossrefType "posted-content" @default.
- W2794804527 hasAuthorship W2794804527A5052883326 @default.
- W2794804527 hasAuthorship W2794804527A5060340617 @default.
- W2794804527 hasAuthorship W2794804527A5073806117 @default.
- W2794804527 hasBestOaLocation W27948045271 @default.
- W2794804527 hasConcept C105795698 @default.
- W2794804527 hasConcept C107673813 @default.
- W2794804527 hasConcept C111350023 @default.
- W2794804527 hasConcept C121332964 @default.
- W2794804527 hasConcept C121683094 @default.
- W2794804527 hasConcept C121864883 @default.
- W2794804527 hasConcept C13153151 @default.
- W2794804527 hasConcept C132725507 @default.
- W2794804527 hasConcept C160234255 @default.
- W2794804527 hasConcept C19499675 @default.
- W2794804527 hasConcept C2780004032 @default.
- W2794804527 hasConcept C28826006 @default.
- W2794804527 hasConcept C33923547 @default.
- W2794804527 hasConcept C37669827 @default.
- W2794804527 hasConcept C41008148 @default.
- W2794804527 hasConcept C62644790 @default.
- W2794804527 hasConceptScore W2794804527C105795698 @default.
- W2794804527 hasConceptScore W2794804527C107673813 @default.
- W2794804527 hasConceptScore W2794804527C111350023 @default.
- W2794804527 hasConceptScore W2794804527C121332964 @default.
- W2794804527 hasConceptScore W2794804527C121683094 @default.
- W2794804527 hasConceptScore W2794804527C121864883 @default.
- W2794804527 hasConceptScore W2794804527C13153151 @default.
- W2794804527 hasConceptScore W2794804527C132725507 @default.
- W2794804527 hasConceptScore W2794804527C160234255 @default.
- W2794804527 hasConceptScore W2794804527C19499675 @default.
- W2794804527 hasConceptScore W2794804527C2780004032 @default.
- W2794804527 hasConceptScore W2794804527C28826006 @default.
- W2794804527 hasConceptScore W2794804527C33923547 @default.
- W2794804527 hasConceptScore W2794804527C37669827 @default.
- W2794804527 hasConceptScore W2794804527C41008148 @default.
- W2794804527 hasConceptScore W2794804527C62644790 @default.
- W2794804527 hasLocation W27948045271 @default.
- W2794804527 hasOpenAccess W2794804527 @default.
- W2794804527 hasPrimaryLocation W27948045271 @default.
- W2794804527 hasRelatedWork W1526488073 @default.
- W2794804527 hasRelatedWork W1592208634 @default.
- W2794804527 hasRelatedWork W2081241186 @default.
- W2794804527 hasRelatedWork W2108651330 @default.
- W2794804527 hasRelatedWork W2155294049 @default.
- W2794804527 hasRelatedWork W2379953892 @default.
- W2794804527 hasRelatedWork W2527992762 @default.
- W2794804527 hasRelatedWork W2883727740 @default.
- W2794804527 hasRelatedWork W2968044004 @default.
- W2794804527 hasRelatedWork W3036600315 @default.
- W2794804527 isParatext "false" @default.
- W2794804527 isRetracted "false" @default.
- W2794804527 magId "2794804527" @default.
- W2794804527 workType "article" @default.