A stable particle filter for a class of high-dimensional state-space models

DOI10.1017/APR.2016.77MaRDI QIDQ5233157zbMATH OpenOpenAlexFDO

Authors Alexandros Beskos, Ajay Jasra, Kengo Kamatani, Yan Zhou, Dan Crisan

Publication date 16 September 2019

Published in Advances in Applied Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1412.3501, http://discovery.ucl.ac.uk/1556083/

zbMATH Keywords

state-space modelhigh dimensionsparticle filter

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Signal detection and filtering (aspects of stochastic processes) (60G35)

Abstract: We consider the numerical approximation of the filtering problem in high dimensions, that is, when the hidden state lies in $mathbb{R}^d$ with $d$ large. For low dimensional problems, one of the most popular numerical procedures for consistent inference is the class of approximations termed particle filters or sequential Monte Carlo methods. However, in high dimensions, standard particle filters (e.g. the bootstrap particle filter) can have a cost that is exponential in $d$ for the algorithm to be stable in an appropriate sense. We develop a new particle filter, called the emph{space-time particle filter}, for a specific family of state-space models in discrete time. This new class of particle filters provide consistent Monte Carlo estimates for any fixed $d$, as do standard particle filters. Moreover, we expect that the state-space particle filter will scale much better with $d$ than the standard filter. We illustrate this analytically for a model of a simple i.i.d. structure and one of a Markovian structure in the $d$-dimensional space-direction, when we show that the algorithm exhibits certain stability properties as $d$ increases at a cost $mathcalO(nN{d}^2)$, where $n$ is the time parameter and $N$ is the number of Monte Carlo samples, that are fixed and independent of $d$. Similar results are expected to hold, under a more general structure than the i.i.d.~one. independently of the dimension. Our theoretical results are also supported by numerical simulations on practical models of complex structures. The results suggest that it is indeed possible to tackle some high dimensional filtering problems using the space-time particle filter that standard particle filters cannot handle.

Recommendations

• A lagged particle filter for stable filtering of certain high-dimensional state-space models
• Can local particle filters beat the curse of dimensionality?
• scientific article; zbMATH DE number 6469926
• Stability properties of some particle filters
• How to avoid the curse of dimensionality: scalability of particle filters with and without importance weights

Cites work

• scientific article; zbMATH DE number 5919872 (Why is no real title available?)
• scientific article; zbMATH DE number 4174133 (Why is no real title available?)
• scientific article; zbMATH DE number 2106098 (Why is no real title available?)
• A lognormal central limit theorem for particle approximations of normalizing constants
• A nonasymptotic theorem for unnormalized Feynman-Kac particle models
• Can local particle filters beat the curse of dimensionality?
• Error bounds and normalising constants for sequential Monte Carlo samplers in high dimensions
• Mean field simulation for Monte Carlo integration
• On adaptive resampling strategies for sequential Monte Carlo methods
• On parallel implementation of sequential Monte Carlo methods: the island particle model
• On the stability of sequential Monte Carlo methods in high dimensions
• Particle approximations of the score and observed information matrix in state space models with application to parameter estimation
• Sequential Monte Carlo Samplers
• Sequential Monte Carlo methods for high-dimensional inverse problems: a case study for the Navier-Stokes equations

Cited in

(31)

• Numerically modeling stochastic Lie transport in fluid dynamics
• A divide and conquer sequential Monte Carlo approach to high dimensional filtering
• An iterated block particle filter for inference on coupled dynamic systems with shared and unit-specific parameters
• A method for high-dimensional smoothing
• Sequential estimation of temporally evolving latent space network models
• An algorithm for non-parametric estimation in state-space models
• A lagged particle filter for stable filtering of certain high-dimensional state-space models
• Accuracy of some approximate Gaussian filters for the Navier-Stokes equation in the presence of model error
• Ensemble Kalman methods for high-dimensional hierarchical dynamic space-time models
• Importance sampling: intrinsic dimension and computational cost
• Stochastic geometric models with non-stationary spatial correlations in Lagrangian fluid flows
• A particle filter for stochastic advection by Lie transport: a case study for the damped and forced incompressible two-dimensional Euler equation
• Multilevel ensemble Kalman filtering for spatio-temporal processes
• Efficient estimation and particle filter for max-stable processes
• Stratified epidemic model using a latent marked Hawkes process
• Spatiotemporal blocking of the bouncy particle sampler for efficient inference in state-space models
• Sequential Monte Carlo methods for Bayesian elliptic inverse problems
• Can local particle filters beat the curse of dimensionality?
• Inference on high-dimensional implicit dynamic models using a guided intermediate resampling filter
• Sequential discretization schemes for a class of stochastic differential equations and their application to Bayesian filtering
• Stability properties of some particle filters
• How to avoid the curse of dimensionality: scalability of particle filters with and without importance weights
• Clustered exact Daum-Huang particle flow filter
• Bagged Filters for Partially Observed Interacting Systems
• Particle Filtering for Stochastic Navier--Stokes Signal Observed with Linear Additive Noise
• Unbiased multi-index Monte Carlo
• Asymptotic properties of particle filter-based maximum likelihood estimators for state space models
• Real-time estimation and prediction of unsteady flows using reduced-order models coupled with few measurements
• On spatially correlated observations in importance sampling methods for subsidence estimation
• Some contributions to sequential Monte Carlo methods for option pricing
• Data assimilation -- mathematical foundation and applications. Abstracts from the workshop held February 20--26, 2022

This page was built for publication: A stable particle filter for a class of high-dimensional state-space models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5233157)