multilevel_CASPF: Multilevel Conditional Ancestor Sampling Particle Filter

In jeremyhengjm/UnbiasedScore: Unbiased estimators for partially observed diffusions

Multilevel Conditional Ancestor Sampling Particle Filter

Description

Runs two coupled conditional particle filters (one at each discretization level) with ancestor sampling (Lindsten, Jordan and Schon, 2014).

Usage

multilevel_CASPF(
  model,
  theta,
  discretization,
  observations,
  nparticles,
  resampling_threshold,
  coupled_resampling,
  ref_trajectory_coarse = NULL,
  ref_trajectory_fine = NULL,
  treestorage = FALSE
)

Arguments

model	a list representing a hidden Markov model, e.g. hmm_ornstein_uhlenbeck
theta	a vector of parameters as input to model functions
discretization	lists containing stepsize, nsteps, statelength, obstimes for fine and coarse levels, and coarsetimes of length statelength_fine indexing time steps of coarse level
observations	a matrix of observations, of size nobservations x ydimension
nparticles	number of particles
resampling_threshold	ESS proportion below which resampling is triggered (always resample at observation times by default)
coupled_resampling	a 2-way coupled resampling scheme, such as coupled2_maximal_independent_residuals
ref_trajectory_coarse	a matrix of reference trajectory for coarser discretization level, of size xdimension x statelength_coarse
ref_trajectory_fine	a matrix of reference trajectory for finer discretization level, of size xdimension x statelength_fine
treestorage	logical specifying tree storage of Jacob, Murray and Rubenthaler (2013); if missing, this function store all states and ancestors

Value

two new trajectories stored as matrices of size xdimension x statelength_coarse/fine.

jeremyhengjm/UnbiasedScore documentation built on Nov. 17, 2023, 1:48 a.m.