Backward Map for Filter Stability Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Jin Won, Joshi, Anant A., Mehta, Prashant G.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909341260447744
author Kim, Jin Won
Joshi, Anant A.
Mehta, Prashant G.
author_facet Kim, Jin Won
Joshi, Anant A.
Mehta, Prashant G.
contents In this paper, a backward map is introduced for the purposes of analysis of the nonlinear (stochastic) filter stability. The backward map is important because the filter-stability in the sense of $\chisq$-divergence follows from showing a certain variance decay property for the backward map. To show this property requires additional assumptions on the model properties of the hidden Markov model (HMM). The analysis in this paper is based on introducing a Poincaré Inequality (PI) for HMMs with white noise observations. In finite state-space settings, PI is related to both the ergodicity of the Markov process as well as the observability of the HMM. It is shown that the Poincaré constant is positive if and only if the HMM is detectable.
format Preprint
id arxiv_https___arxiv_org_abs_2405_01127
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Backward Map for Filter Stability Analysis
Kim, Jin Won
Joshi, Anant A.
Mehta, Prashant G.
Probability
Optimization and Control
In this paper, a backward map is introduced for the purposes of analysis of the nonlinear (stochastic) filter stability. The backward map is important because the filter-stability in the sense of $\chisq$-divergence follows from showing a certain variance decay property for the backward map. To show this property requires additional assumptions on the model properties of the hidden Markov model (HMM). The analysis in this paper is based on introducing a Poincaré Inequality (PI) for HMMs with white noise observations. In finite state-space settings, PI is related to both the ergodicity of the Markov process as well as the observability of the HMM. It is shown that the Poincaré constant is positive if and only if the HMM is detectable.
title Backward Map for Filter Stability Analysis
topic Probability
Optimization and Control
url https://arxiv.org/abs/2405.01127