Matches in SemOpenAlex for { <https://semopenalex.org/work/W2886496274> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2886496274 abstract "Statistical inference methods are fundamentally important in machine learning. Most state-of-the-art inference algorithms are variants of Markov chain Monte Carlo (MCMC) or variational inference (VI). However, both methods struggle with limitations in practice: MCMC methods can be computationally demanding; VI methods may have large bias. In this work, we aim to improve upon MCMC and VI by a novel hybrid method based on the idea of reducing simulation bias of finite-length MCMC chains using gradient-based optimisation. The proposed method can generate low-biased samples by increasing the length of MCMC simulation and optimising the MCMC hyper-parameters, which offers attractive balance between approximation bias and computational efficiency. We show that our method produces promising results on popular benchmarks when compared to recent hybrid methods of MCMC and VI." @default.
- W2886496274 created "2018-08-22" @default.
- W2886496274 creator A5008397618 @default.
- W2886496274 creator A5010820865 @default.
- W2886496274 creator A5029396252 @default.
- W2886496274 date "2018-09-27" @default.
- W2886496274 modified "2023-09-24" @default.
- W2886496274 title "Ergodic Measure Preserving Flows" @default.
- W2886496274 cites W130710483 @default.
- W2886496274 cites W1503398984 @default.
- W2886496274 cites W1545319692 @default.
- W2886496274 cites W177847060 @default.
- W2886496274 cites W1833498382 @default.
- W2886496274 cites W1880262756 @default.
- W2886496274 cites W1906598733 @default.
- W2886496274 cites W1959608418 @default.
- W2886496274 cites W2080972498 @default.
- W2886496274 cites W2116064496 @default.
- W2886496274 cites W2126008947 @default.
- W2886496274 cites W2165363188 @default.
- W2886496274 cites W2319437274 @default.
- W2886496274 cites W2478027467 @default.
- W2886496274 cites W2556372419 @default.
- W2886496274 cites W2587284713 @default.
- W2886496274 cites W2739517340 @default.
- W2886496274 cites W2750384547 @default.
- W2886496274 cites W2963090522 @default.
- W2886496274 cites W2963971375 @default.
- W2886496274 cites W2964121744 @default.
- W2886496274 hasPublicationYear "2018" @default.
- W2886496274 type Work @default.
- W2886496274 sameAs 2886496274 @default.
- W2886496274 citedByCount "4" @default.
- W2886496274 countsByYear W28864962742019 @default.
- W2886496274 countsByYear W28864962742020 @default.
- W2886496274 crossrefType "posted-content" @default.
- W2886496274 hasAuthorship W2886496274A5008397618 @default.
- W2886496274 hasAuthorship W2886496274A5010820865 @default.
- W2886496274 hasAuthorship W2886496274A5029396252 @default.
- W2886496274 hasConcept C105795698 @default.
- W2886496274 hasConcept C107673813 @default.
- W2886496274 hasConcept C111350023 @default.
- W2886496274 hasConcept C11413529 @default.
- W2886496274 hasConcept C119857082 @default.
- W2886496274 hasConcept C122044880 @default.
- W2886496274 hasConcept C124101348 @default.
- W2886496274 hasConcept C126255220 @default.
- W2886496274 hasConcept C134306372 @default.
- W2886496274 hasConcept C154945302 @default.
- W2886496274 hasConcept C19499675 @default.
- W2886496274 hasConcept C2776214188 @default.
- W2886496274 hasConcept C2780009758 @default.
- W2886496274 hasConcept C33923547 @default.
- W2886496274 hasConcept C41008148 @default.
- W2886496274 hasConceptScore W2886496274C105795698 @default.
- W2886496274 hasConceptScore W2886496274C107673813 @default.
- W2886496274 hasConceptScore W2886496274C111350023 @default.
- W2886496274 hasConceptScore W2886496274C11413529 @default.
- W2886496274 hasConceptScore W2886496274C119857082 @default.
- W2886496274 hasConceptScore W2886496274C122044880 @default.
- W2886496274 hasConceptScore W2886496274C124101348 @default.
- W2886496274 hasConceptScore W2886496274C126255220 @default.
- W2886496274 hasConceptScore W2886496274C134306372 @default.
- W2886496274 hasConceptScore W2886496274C154945302 @default.
- W2886496274 hasConceptScore W2886496274C19499675 @default.
- W2886496274 hasConceptScore W2886496274C2776214188 @default.
- W2886496274 hasConceptScore W2886496274C2780009758 @default.
- W2886496274 hasConceptScore W2886496274C33923547 @default.
- W2886496274 hasConceptScore W2886496274C41008148 @default.
- W2886496274 hasLocation W28864962741 @default.
- W2886496274 hasOpenAccess W2886496274 @default.
- W2886496274 hasPrimaryLocation W28864962741 @default.
- W2886496274 hasRelatedWork W153946686 @default.
- W2886496274 hasRelatedWork W1987558550 @default.
- W2886496274 hasRelatedWork W2040276592 @default.
- W2886496274 hasRelatedWork W2070873660 @default.
- W2886496274 hasRelatedWork W2104694069 @default.
- W2886496274 hasRelatedWork W2762418104 @default.
- W2886496274 hasRelatedWork W2768001799 @default.
- W2886496274 hasRelatedWork W2803598280 @default.
- W2886496274 hasRelatedWork W2947432301 @default.
- W2886496274 hasRelatedWork W2950402421 @default.
- W2886496274 hasRelatedWork W2958192850 @default.
- W2886496274 hasRelatedWork W2963554070 @default.
- W2886496274 hasRelatedWork W2963636084 @default.
- W2886496274 hasRelatedWork W2977230103 @default.
- W2886496274 hasRelatedWork W2983289675 @default.
- W2886496274 hasRelatedWork W2994552149 @default.
- W2886496274 hasRelatedWork W3008391717 @default.
- W2886496274 hasRelatedWork W3047714077 @default.
- W2886496274 hasRelatedWork W3108233352 @default.
- W2886496274 hasRelatedWork W3132406668 @default.
- W2886496274 isParatext "false" @default.
- W2886496274 isRetracted "false" @default.
- W2886496274 magId "2886496274" @default.
- W2886496274 workType "article" @default.