• Corpus ID: 239049540

Iterated Block Particle Filter for High-dimensional Parameter Learning: Beating the Curse of Dimensionality

  title={Iterated Block Particle Filter for High-dimensional Parameter Learning: Beating the Curse of Dimensionality},
  author={Ning Ning and Edward L. Ionides},
Parameter learning for high-dimensional, partially observed, and nonlinear stochastic processes is a methodological challenge. Spatiotemporal disease transmission systems provide examples of such processes giving rise to open inference problems. We propose the iterated block particle filter (IBPF) algorithm for learning high-dimensional parameters over graphical state space models with general state spaces, measures, transition densities and graph structure. Theoretical performance guarantees… 

Figures and Tables from this paper


Ensemble Kalman Methods for High-Dimensional Hierarchical Dynamic Space-Time Models
A new class of filtering and smoothing methods for inference in high-dimensional, nonlinear, non-Gaussian, spatio-temporal state-space models, developed in the geophysics literature and statistics literature is proposed, with a Bayesian perspective.
Can local particle filters beat the curse of dimensionality
It is argued that it is often possible, at least in principle, to develop local particle filtering algorithms whose approximation error is dimension-free and the key to such developments is the decay of correlations property, which is a spatial counterpart of the much better understood stability property of nonlinear filters.
The Iterated Auxiliary Particle Filter
ABSTRACT We present an offline, iterated particle filter to facilitate statistical inference in general state space hidden Markov models. Given a model and a sequence of observations, the associated
Obstacles to High-Dimensional Particle Filtering
Abstract Particle filters are ensemble-based assimilation schemes that, unlike the ensemble Kalman filter, employ a fully nonlinear and non-Gaussian analysis step to compute the probability
Curse-of-dimensionality revisited: Collapse of the particle filter in very large scale systems
It is demonstrated that the maximum of the weights associated with the sample ensemble converges to one as both the sample size and the system dimension tends to infinity, and the weight singularity is established in models with more general multivariate likelihoods, e.g. Gaussian and Cauchy.
Inference for dynamic and latent variable models via iterated, perturbed Bayes maps
A new theoretical framework for iterated filtering is developed and an algorithm supported by this theory displays substantial numerical improvement on the computational challenge of inferring parameters of a partially observed Markov process.
Twisted particle filters
We investigate sampling laws for particle algorithms and the influence of these laws on the efficiency of particle approximations of marginal likelihoods in hidden Markov models. Among a broad class
On Blocks, Tempering and Particle MCMC for Systems Identification
Inference for nonlinear dynamical systems
This work presents a new method that makes maximum likelihood estimation feasible for partially-observed nonlinear stochastic dynamical systems (also known as state-space models) where this was not previously the case.
Comparison of Ensemble Kalman Filters under Non-Gaussianity
Abstract Recently various versions of ensemble Kalman filters (EnKFs) have been proposed and studied. This work concerns, in a mathematically rigorous manner, the relative performance of two major