6533b825fe1ef96bd12820c4
RESEARCH PRODUCT
Particle Group Metropolis Methods for Tracking the Leaf Area Index
Gustau Camps-vallsLuca MartinoVictor Elvirasubject
Signal processing010504 meteorology & atmospheric sciencesMarkov chainGeneralizationComputer scienceBayesian inferenceMonte Carlo method020206 networking & telecommunicationsMarkov chain Monte Carlo02 engineering and technologystate-space modelsTracking (particle physics)Bayesian inference01 natural sciencesParticle FilteringStatistics::Computationsymbols.namesake0202 electrical engineering electronic engineering information engineeringsymbolsParticle MCMCParticle filterMonte CarloAlgorithm0105 earth and related environmental sciencesdescription
Monte Carlo (MC) algorithms are widely used for Bayesian inference in statistics, signal processing, and machine learning. In this work, we introduce an Markov Chain Monte Carlo (MCMC) technique driven by a particle filter. The resulting scheme is a generalization of the so-called Particle Metropolis-Hastings (PMH) method, where a suitable Markov chain of sets of weighted samples is generated. We also introduce a marginal version for the goal of jointly inferring dynamic and static variables. The proposed algorithms outperform the corresponding standard PMH schemes, as shown by numerical experiments.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2020-01-01 |