Exponential forgetting of smoothing distributions for pairwise Markov models

TL;DR

This paper establishes conditions under which smoothing, filtering, and predictive probabilities in pairwise Markov models converge exponentially, including for hidden Markov models, with general and verifiable assumptions.

Contribution

It provides new sufficient conditions for exponential convergence of smoothing distributions in pairwise Markov models, extending to hidden Markov models with more general assumptions.

Findings

Exponential convergence of smoothing probabilities is guaranteed under general conditions.

Conditions are more general than existing mixing-type assumptions.

Results apply to hidden Markov models and are easy to verify.

Abstract

We consider a bivariate Markov chain $Z=\{Z_k\}_{k \geq 1}=\{(X_k,Y_k)\}_{k \geq 1}$ taking values on product space ${\cal Z}={\cal X} \times{ \cal Y}$, where ${\cal X}$ is possibly uncountable space and ${\cal Y}=\{1,\ldots, |{\cal Y}|\}$ is a finite state-space. The purpose of the paper is to find sufficient conditions that guarantee the exponential convergence of smoothing, filtering and predictive probabilities: $$\sup_{n\geq t}\|P(Y_{t:\infty}\in \cdot|X_{l:n})-P(Y_{t:\infty}\in \cdot|X_{s:n}) \|_{\rm TV} \leq K_s \alpha^{t}, \quad \mbox{a.s.}$$ Here $t\geq s\geq l\geq 1$, $K_s$ is $\sigma(X_{s:\infty})$-measurable finite random variable and $\alpha\in (0,1)$ is fixed. In the second part of the paper, we establish two-sided versions of the above-mentioned convergence. We show that the desired convergences hold under fairly general conditions. A special case of above-mentioned very general model is popular hidden Markov model (HMM). We prove that in HMM-case, our assumptions are more general than all similar mixing-type of conditions encountered in practice, yet relatively easy to verify.