Matches in SemOpenAlex for { <https://semopenalex.org/work/W2806674516> ?p ?o ?g. }
- W2806674516 abstract "Stein variational gradient descent (SVGD) was recently proposed as a general purpose nonparametric variational inference algorithm [Liu & Wang, NIPS 2016]: it minimizes the Kullback-Leibler divergence between the target distribution and its approximation by implementing a form of functional gradient descent on a reproducing kernel Hilbert space. In this paper, we accelerate and generalize the SVGD algorithm by including second-order information, thereby approximating a Newton-like iteration in function space. We also show how second-order information can lead to more effective choices of kernel. We observe significant computational gains over the original SVGD algorithm in multiple test cases." @default.
- W2806674516 created "2018-06-13" @default.
- W2806674516 creator A5003445227 @default.
- W2806674516 creator A5019138446 @default.
- W2806674516 creator A5050544926 @default.
- W2806674516 creator A5067931953 @default.
- W2806674516 creator A5071702167 @default.
- W2806674516 date "2018-06-08" @default.
- W2806674516 modified "2023-09-27" @default.
- W2806674516 title "A Stein variational Newton method" @default.
- W2806674516 cites W1534416612 @default.
- W2806674516 cites W1545319692 @default.
- W2806674516 cites W1703999417 @default.
- W2806674516 cites W1856621748 @default.
- W2806674516 cites W1986280275 @default.
- W2806674516 cites W2082261407 @default.
- W2806674516 cites W2104067967 @default.
- W2806674516 cites W2130416410 @default.
- W2806674516 cites W2142737094 @default.
- W2806674516 cites W2149498546 @default.
- W2806674516 cites W2478027467 @default.
- W2806674516 cites W2606757878 @default.
- W2806674516 cites W2608990917 @default.
- W2806674516 cites W2609758862 @default.
- W2806674516 cites W2769671561 @default.
- W2806674516 cites W2769747564 @default.
- W2806674516 cites W2773022682 @default.
- W2806674516 cites W2774598382 @default.
- W2806674516 cites W2951406958 @default.
- W2806674516 cites W2962752165 @default.
- W2806674516 cites W2963090522 @default.
- W2806674516 cites W2963849628 @default.
- W2806674516 cites W2963956018 @default.
- W2806674516 cites W3029645440 @default.
- W2806674516 cites W3098700198 @default.
- W2806674516 cites W385466589 @default.
- W2806674516 hasPublicationYear "2018" @default.
- W2806674516 type Work @default.
- W2806674516 sameAs 2806674516 @default.
- W2806674516 citedByCount "28" @default.
- W2806674516 countsByYear W28066745162018 @default.
- W2806674516 countsByYear W28066745162019 @default.
- W2806674516 countsByYear W28066745162020 @default.
- W2806674516 countsByYear W28066745162021 @default.
- W2806674516 crossrefType "posted-content" @default.
- W2806674516 hasAuthorship W2806674516A5003445227 @default.
- W2806674516 hasAuthorship W2806674516A5019138446 @default.
- W2806674516 hasAuthorship W2806674516A5050544926 @default.
- W2806674516 hasAuthorship W2806674516A5067931953 @default.
- W2806674516 hasAuthorship W2806674516A5071702167 @default.
- W2806674516 hasConcept C102366305 @default.
- W2806674516 hasConcept C105795698 @default.
- W2806674516 hasConcept C111919701 @default.
- W2806674516 hasConcept C11413529 @default.
- W2806674516 hasConcept C126255220 @default.
- W2806674516 hasConcept C134306372 @default.
- W2806674516 hasConcept C138885662 @default.
- W2806674516 hasConcept C14036430 @default.
- W2806674516 hasConcept C142730499 @default.
- W2806674516 hasConcept C153258448 @default.
- W2806674516 hasConcept C154945302 @default.
- W2806674516 hasConcept C171752962 @default.
- W2806674516 hasConcept C202444582 @default.
- W2806674516 hasConcept C207390915 @default.
- W2806674516 hasConcept C2776214188 @default.
- W2806674516 hasConcept C2778572836 @default.
- W2806674516 hasConcept C28826006 @default.
- W2806674516 hasConcept C33923547 @default.
- W2806674516 hasConcept C41008148 @default.
- W2806674516 hasConcept C41895202 @default.
- W2806674516 hasConcept C50644808 @default.
- W2806674516 hasConcept C62799726 @default.
- W2806674516 hasConcept C74193536 @default.
- W2806674516 hasConcept C78458016 @default.
- W2806674516 hasConcept C80884492 @default.
- W2806674516 hasConcept C86803240 @default.
- W2806674516 hasConceptScore W2806674516C102366305 @default.
- W2806674516 hasConceptScore W2806674516C105795698 @default.
- W2806674516 hasConceptScore W2806674516C111919701 @default.
- W2806674516 hasConceptScore W2806674516C11413529 @default.
- W2806674516 hasConceptScore W2806674516C126255220 @default.
- W2806674516 hasConceptScore W2806674516C134306372 @default.
- W2806674516 hasConceptScore W2806674516C138885662 @default.
- W2806674516 hasConceptScore W2806674516C14036430 @default.
- W2806674516 hasConceptScore W2806674516C142730499 @default.
- W2806674516 hasConceptScore W2806674516C153258448 @default.
- W2806674516 hasConceptScore W2806674516C154945302 @default.
- W2806674516 hasConceptScore W2806674516C171752962 @default.
- W2806674516 hasConceptScore W2806674516C202444582 @default.
- W2806674516 hasConceptScore W2806674516C207390915 @default.
- W2806674516 hasConceptScore W2806674516C2776214188 @default.
- W2806674516 hasConceptScore W2806674516C2778572836 @default.
- W2806674516 hasConceptScore W2806674516C28826006 @default.
- W2806674516 hasConceptScore W2806674516C33923547 @default.
- W2806674516 hasConceptScore W2806674516C41008148 @default.
- W2806674516 hasConceptScore W2806674516C41895202 @default.
- W2806674516 hasConceptScore W2806674516C50644808 @default.
- W2806674516 hasConceptScore W2806674516C62799726 @default.
- W2806674516 hasConceptScore W2806674516C74193536 @default.
- W2806674516 hasConceptScore W2806674516C78458016 @default.