Matches in SemOpenAlex for { <https://semopenalex.org/work/W3099693596> ?p ?o ?g. }
- W3099693596 endingPage "92" @default.
- W3099693596 startingPage "81" @default.
- W3099693596 abstract "Particle Metropolis-Hastings (PMH) allows for Bayesian parameter inference in nonlinear state space models by combining Markov chain Monte Carlo (MCMC) and particle filtering. The latter is used to estimate the intractable likelihood. In its original formulation, PMH makes use of a marginal MCMC proposal for the parameters, typically a Gaussian random walk. However, this can lead to a poor exploration of the parameter space and an inefficient use of the generated particles. We propose a number of alternative versions of PMH that incorporate gradient and Hessian information about the posterior into the proposal. This information is more or less obtained as a byproduct of the likelihood estimation. Indeed, we show how to estimate the required information using a fixed-lag particle smoother, with a computational cost growing linearly in the number of particles. We conclude that the proposed methods can: (i) decrease the length of the burn-in phase, (ii) increase the mixing of the Markov chain at the stationary phase, and (iii) make the proposal distribution scale invariant which simplifies tuning." @default.
- W3099693596 created "2020-11-23" @default.
- W3099693596 creator A5045048407 @default.
- W3099693596 creator A5083090794 @default.
- W3099693596 creator A5089607178 @default.
- W3099693596 date "2014-09-20" @default.
- W3099693596 modified "2023-10-16" @default.
- W3099693596 title "Particle Metropolis–Hastings using gradient and Hessian information" @default.
- W3099693596 cites W1501586228 @default.
- W3099693596 cites W1545050323 @default.
- W3099693596 cites W1556278552 @default.
- W3099693596 cites W1830883013 @default.
- W3099693596 cites W1964491534 @default.
- W3099693596 cites W2010522529 @default.
- W3099693596 cites W2029164135 @default.
- W3099693596 cites W2030911724 @default.
- W3099693596 cites W2031294093 @default.
- W3099693596 cites W2043983054 @default.
- W3099693596 cites W2051768929 @default.
- W3099693596 cites W2059448777 @default.
- W3099693596 cites W2082542916 @default.
- W3099693596 cites W2088311145 @default.
- W3099693596 cites W2090251478 @default.
- W3099693596 cites W2091860746 @default.
- W3099693596 cites W2094227853 @default.
- W3099693596 cites W2098613108 @default.
- W3099693596 cites W2106949461 @default.
- W3099693596 cites W2111980769 @default.
- W3099693596 cites W2122028584 @default.
- W3099693596 cites W2131598171 @default.
- W3099693596 cites W2135973421 @default.
- W3099693596 cites W2165321580 @default.
- W3099693596 cites W4233487859 @default.
- W3099693596 cites W4250389103 @default.
- W3099693596 cites W4292691288 @default.
- W3099693596 doi "https://doi.org/10.1007/s11222-014-9510-0" @default.
- W3099693596 hasPublicationYear "2014" @default.
- W3099693596 type Work @default.
- W3099693596 sameAs 3099693596 @default.
- W3099693596 citedByCount "21" @default.
- W3099693596 countsByYear W30996935962015 @default.
- W3099693596 countsByYear W30996935962016 @default.
- W3099693596 countsByYear W30996935962017 @default.
- W3099693596 countsByYear W30996935962018 @default.
- W3099693596 countsByYear W30996935962019 @default.
- W3099693596 countsByYear W30996935962020 @default.
- W3099693596 countsByYear W30996935962022 @default.
- W3099693596 countsByYear W30996935962023 @default.
- W3099693596 crossrefType "journal-article" @default.
- W3099693596 hasAuthorship W3099693596A5045048407 @default.
- W3099693596 hasAuthorship W3099693596A5083090794 @default.
- W3099693596 hasAuthorship W3099693596A5089607178 @default.
- W3099693596 hasBestOaLocation W30996935962 @default.
- W3099693596 hasConcept C105795698 @default.
- W3099693596 hasConcept C107673813 @default.
- W3099693596 hasConcept C111350023 @default.
- W3099693596 hasConcept C11413529 @default.
- W3099693596 hasConcept C121332964 @default.
- W3099693596 hasConcept C126255220 @default.
- W3099693596 hasConcept C157286648 @default.
- W3099693596 hasConcept C160234255 @default.
- W3099693596 hasConcept C163716315 @default.
- W3099693596 hasConcept C167928553 @default.
- W3099693596 hasConcept C177769412 @default.
- W3099693596 hasConcept C203616005 @default.
- W3099693596 hasConcept C204693719 @default.
- W3099693596 hasConcept C28826006 @default.
- W3099693596 hasConcept C33923547 @default.
- W3099693596 hasConcept C41008148 @default.
- W3099693596 hasConcept C52421305 @default.
- W3099693596 hasConcept C57830394 @default.
- W3099693596 hasConcept C62520636 @default.
- W3099693596 hasConcept C89106044 @default.
- W3099693596 hasConcept C95923904 @default.
- W3099693596 hasConcept C98763669 @default.
- W3099693596 hasConceptScore W3099693596C105795698 @default.
- W3099693596 hasConceptScore W3099693596C107673813 @default.
- W3099693596 hasConceptScore W3099693596C111350023 @default.
- W3099693596 hasConceptScore W3099693596C11413529 @default.
- W3099693596 hasConceptScore W3099693596C121332964 @default.
- W3099693596 hasConceptScore W3099693596C126255220 @default.
- W3099693596 hasConceptScore W3099693596C157286648 @default.
- W3099693596 hasConceptScore W3099693596C160234255 @default.
- W3099693596 hasConceptScore W3099693596C163716315 @default.
- W3099693596 hasConceptScore W3099693596C167928553 @default.
- W3099693596 hasConceptScore W3099693596C177769412 @default.
- W3099693596 hasConceptScore W3099693596C203616005 @default.
- W3099693596 hasConceptScore W3099693596C204693719 @default.
- W3099693596 hasConceptScore W3099693596C28826006 @default.
- W3099693596 hasConceptScore W3099693596C33923547 @default.
- W3099693596 hasConceptScore W3099693596C41008148 @default.
- W3099693596 hasConceptScore W3099693596C52421305 @default.
- W3099693596 hasConceptScore W3099693596C57830394 @default.
- W3099693596 hasConceptScore W3099693596C62520636 @default.
- W3099693596 hasConceptScore W3099693596C89106044 @default.
- W3099693596 hasConceptScore W3099693596C95923904 @default.
- W3099693596 hasConceptScore W3099693596C98763669 @default.
- W3099693596 hasIssue "1" @default.