The infinite viterbi alignment and decay-convexity

DOI10.3150/23-BEJ1596MaRDI QIDQ6178559zbMATH OpenOpenAlexFDO

Authors Nick Whiteley, Matt W. Jones, Aleks P. F. Domanski

Publication date 16 January 2024

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1810.04115

zbMATH Keywords

convex optimizationhidden Markov modelsMAP estimationparallelization

Mathematics Subject Classification ID

Markov processes (60Jxx) Parametric inference (62Fxx) Inference from stochastic processes (62Mxx)

Abstract: The infinite Viterbi alignment is the limiting maximum a-posteriori estimate of the unobserved path in a hidden Markov model as the length of the time horizon grows. For models on state-space $mathbb{R}^d$ satisfying a new ``decay-convexity condition, we develop an approach to existence of the infinite Viterbi alignment in an infinite dimensional Hilbert space. Quantitative bounds on the distance to the infinite Viterbi alignment, which are the first of their kind, are derived and used to illustrate how approximate estimation via parallelization can be accurate and scaleable to high-dimensional problems because the rate of convergence to the infinite Viterbi alignment does not necessarily depend on $d$. The results are applied to approximate estimation via parallelization and a model of neural population activity.

Cites work

• A Constructive Proof of the Existence of Viterbi Processes
• Asymptotic properties of the maximum likelihood estimation in misspecified hidden Markov models
• Asymptotic risks of Viterbi segmentation
• Bayesian forecasting and dynamic models
• Convergence of the maximum a posteriori path estimator in hidden Markov models
• Existence of infinite Viterbi path for pairwise Markov models
• Forgetting the initial distribution for hidden Markov models
• Infinite Viterbi alignments in the two state hidden Markov models
• Log-concavity and strong log-concavity: a review
• Nonlinear time series. Theory, methods and applications with R examples
• On the Viterbi process with continuous state space
• Ordinary differential equations in Banach spaces
• Properties of the maximum a posteriori path estimator in hidden Markov models
• Regenerativity of Viterbi process for pairwise Markov models
• The adjusted Viterbi training for hidden Markov models
• The Ricci flow in Riemannian geometry. A complete proof of the differentiable 1/4-pinching sphere theorem
• Time series analysis by state space methods.

This page was built for publication: The infinite viterbi alignment and decay-convexity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6178559)