Next Article in Journal
Semi-Classical Discretization and Long-Time Evolution of Variable Spin Systems
Next Article in Special Issue
Improved Local Search with Momentum for Bayesian Networks Structure Learning
Previous Article in Journal
Causality Is an Effect, II
Previous Article in Special Issue
Inference and Learning in a Latent Variable Model for Beta Distributed Interval Data
Article

Message Passing-Based Inference for Time-Varying Autoregressive Models

1
Department of Electrical Engineering, Eindhoven University of Technology, 5612 AZ Eindhoven, The Netherlands
2
GN Hearing, JF Kennedylaan 2, 5612 AB Eindhoven, The Netherlands
*
Author to whom correspondence should be addressed.
Academic Editor: Rafael Rumí
Entropy 2021, 23(6), 683; https://doi.org/10.3390/e23060683
Received: 18 April 2021 / Revised: 21 May 2021 / Accepted: 24 May 2021 / Published: 28 May 2021
(This article belongs to the Special Issue Bayesian Inference in Probabilistic Graphical Models)
Time-varying autoregressive (TVAR) models are widely used for modeling of non-stationary signals. Unfortunately, online joint adaptation of both states and parameters in these models remains a challenge. In this paper, we represent the TVAR model by a factor graph and solve the inference problem by automated message passing-based inference for states and parameters. We derive structured variational update rules for a composite “AR node” with probabilistic observations that can be used as a plug-in module in hierarchical models, for example, to model the time-varying behavior of the hyper-parameters of a time-varying AR model. Our method includes tracking of variational free energy (FE) as a Bayesian measure of TVAR model performance. The proposed methods are verified on a synthetic data set and validated on real-world data from temperature modeling and speech enhancement tasks. View Full-Text
Keywords: Bayesian inference; free energy; factor graph; hybrid message passing; model selection; non-stationary systems; probabilistic graphical models Bayesian inference; free energy; factor graph; hybrid message passing; model selection; non-stationary systems; probabilistic graphical models
Show Figures

Figure 1

MDPI and ACS Style

Podusenko, A.; Kouw, W.M.; de Vries, B. Message Passing-Based Inference for Time-Varying Autoregressive Models. Entropy 2021, 23, 683. https://doi.org/10.3390/e23060683

AMA Style

Podusenko A, Kouw WM, de Vries B. Message Passing-Based Inference for Time-Varying Autoregressive Models. Entropy. 2021; 23(6):683. https://doi.org/10.3390/e23060683

Chicago/Turabian Style

Podusenko, Albert; Kouw, Wouter M.; de Vries, Bert. 2021. "Message Passing-Based Inference for Time-Varying Autoregressive Models" Entropy 23, no. 6: 683. https://doi.org/10.3390/e23060683

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop