Technical Program

Paper Detail

Paper IDG.1.4
Paper Title Online Variational Message Passing in Hierarchical Autoregressive Models
Authors Albert Podusenko, Wouter Marco Kouw, Bert de Vries, Eindhoven University of Technology, Netherlands
Session G.1: Graph Analytics
Presentation Lecture
Track Graphs, Games, Sparsity, and Signal Processing
Manuscript  Click here to download the manuscript
Virtual Presentation  Click here to watch in the Virtual Symposium
Abstract Hierarchical autoregressive (AR) models can describe many complex physical processes. Unfortunately, online adaptation in these models under non-stationary conditions remains a challenge. In this paper, we track states and parameters in a hierarchical AR filter by means of variational message passing (VMP) in a factor graph. We derive VMP update rules for an "AR node” that can be re-used at various hierarchical levels and supports automated message passing-based inference for states and parameters. The proposed method is experimentally validated for a 2-level hierarchical AR model.

Plan Ahead

IEEE ISIT 2021

2021 IEEE International Symposium on Information Theory

11-16 July 2021 | Melbourne, Victoria, Australia

Visit Website!