Exponential filter stability via Dobrushin's coefficient

DOI10.1214/20-ECP333zbMATH Open1468.60051arXiv1910.08463OpenAlexW3047409223WikidataQ115517705 ScholiaQ115517705MaRDI QIDQ2201531FDOQ2201531

Serdar Yüksel, Curtis McDonald

Publication date: 29 September 2020

Published in: Electronic Communications in Probability (Search for Journal in Brave)

Abstract: Filter stability is a classical problem in the study of partially observed Markov processes (POMP), also known as hidden Markov models (HMM). For a POMP, an incorrectly initialized non-linear filter is said to be (asymptotically) stable if the filter eventually corrects itself as more measurements are collected. Filter stability results in the literature that provide rates of convergence typically rely on very restrictive mixing conditions on the transition kernel and measurement kernel pair, and do not consider their effects independently. In this paper, we introduce an alternative approach using the Dobrushin coefficients associated with both the transition kernel as well as the measurement channel. Such a joint study, which seems to have been unexplored, leads to a concise analysis that can be applied to more general system models under relaxed conditions: in particular, we show that if $(1-delta(T))(2-delta(Q))<1$, where $delta(T)$ and $delta(Q)$ are the Dobrushin coefficients for the transition and the measurement kernels, then the filter is exponentially stable. Our findings are also applicable for controlled models.

Full work available at URL: https://arxiv.org/abs/1910.08463

zbMATH Keywords

filter stabilitygeometric convergencenon-linear filteringDobrushin coefficient

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Filtering in stochastic control theory (93E11) Signal detection and filtering (aspects of stochastic processes) (60G35) Discrete-time Markov processes on general state spaces (60J05) Asymptotic stability in control theory (93D20)

Cites Work

• Title not available (Why is that?)
• Stability and uniform approximation of nonlinear filters using the Hilbert metric and application to particle filters
• Inference in hidden Markov models.
• On the stability of interacting processes with applications to filtering and genetic algorithms
• On discrete time ergodic filters with wrong initial data
• Ergodicity of hidden Markov models
• Asymptotic Stability of the Optimal Filter with Respect to Its Initial Condition
• A complete solution to Blackwell's unique ergodicity problem for hidden Markov chains
• Exponential stability for nonlinear filtering
• Exponential stability in discrete-time filtering for non-ergodic signal.
• Stability of nonlinear filters in nonmixing case
• Stability of the discrete time filter in terms of the tails of noise distributions
• Forgetting of the initial distribution for nonergodic hidden Markov chains

Cited In (8)

• Exponential asymptotic stability of time-varying inverse prediction error filters
• Robustness to incorrect models and data-driven learning in average-cost optimal stochastic control
• Robustness to Incorrect Priors and Controlled Filter Stability in Partially Observed Stochastic Control
• On the stability of positive semigroups
• Average cost optimality of partially observed MDPs: contraction of nonlinear filters and existence of optimal solutions and approximations
• Planning and learning in partially observable systems via filter stability
• Title not available (Why is that?)
• Another look at partially observed optimal stochastic control: existence, ergodicity, and approximations without belief-reduction

This page was built for publication: Exponential filter stability via Dobrushin's coefficient

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2201531)