A unification of weighted and unweighted particle filters

DOI10.1137/20M1382404zbMATH Open1491.60054arXiv2011.13804MaRDI QIDQ5065052FDOQ5065052

Authors: Ehsan Abedi, Simone Carlo Surace, Jean-Pascal Pfister 

Publication date: 18 March 2022

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Abstract: Particle filters (PFs), which are successful methods for approximating the solution of the filtering problem, can be divided into two types: weighted and unweighted PFs. It is well known that weighted PFs suffer from the weight degeneracy and curse of dimensionality. To sidestep these issues, unweighted PFs have been gaining attention, though they have their own challenges. The existing literature on these types of PFs is based on distinct approaches. In order to establish a connection, we put forward a framework that unifies weighted and unweighted PFs in the continuous-time filtering problem. We show that the stochastic dynamics of a particle system described by a pair process, representing particles and their importance weights, should satisfy two necessary conditions in order for its distribution to match the solution of the Kushner--Stratonovich equation. In particular, we demonstrate that the bootstrap particle filter (BPF), which relies on importance sampling, and the feedback particle filter (FPF), which is an unweighted PF based on optimal control, arise as special cases from a broad class and that there is a smooth transition between the two. The freedom in designing the PF dynamics opens up potential ways to address the existing issues in the aforementioned algorithms, namely weight degeneracy in the BPF and gain estimation in the FPF.

Full work available at URL: https://arxiv.org/abs/2011.13804

Recommendations

• How to avoid the curse of dimensionality: scalability of particle filters with and without importance weights
• Residual and stratified branching particle filters
• McKean--Vlasov SDEs in Nonlinear Filtering
• A uniformly convergent adaptive particle filter
• Independent Particle Filters

zbMATH Keywords

importance samplingFokker-Planck equationstochastic differential equationsinteracting particle systemsnonlinear filteringKushner-Stratonovich equationMcKean-Vlasov processes

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Stochastic partial differential equations (aspects of stochastic analysis) (60H15) Filtering in stochastic control theory (93E11) Signal detection and filtering (aspects of stochastic processes) (60G35) Stochastic particle methods (65C35)

Cites Work

• Central limit theorem for sequential Monte Carlo methods and its application to Bayesian inference
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Fundamentals of stochastic filtering
• Conditional Markov Processes
• Some geometric calculations on Wasserstein space
• Multivariable feedback particle filter
• On the Differential Equations Satisfied by Conditional Probablitity Densities of Markov Processes, with Applications
• Feedback Particle Filter
• Estimation of a Probability Density Function and Its Derivatives
• Title not available (Why is that?)
• Title not available (Why is that?)
• Data assimilation: the Schrödinger perspective
• Estimation of the derivative of the logarithm of a density
• An Optimal Transport Formulation of the Ensemble Kalman Filter
• Applied stochastic differential equations
• How to avoid the curse of dimensionality: scalability of particle filters with and without importance weights
• McKean--Vlasov SDEs in Nonlinear Filtering
• The Hitchhiker's guide to nonlinear filtering

Cited In (2)

• A uniformly convergent adaptive particle filter
• How to avoid the curse of dimensionality: scalability of particle filters with and without importance weights

This page was built for publication: A unification of weighted and unweighted particle filters

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5065052)