Revisiting Context-Tree Weighting for Bayesian Inference
Authors
Papageorgiou, I
Mertzanis, L
Panotopoulou, A
Skoularidou, M
Change log
Abstract
We revisit the statistical foundation of the celebrated context tree weighting (CTW) algorithm, and we develop a Bayesian modelling framework for the class of higher-order, variable-memory Markov chains, along with an associated collection of methodological tools for exact inference for discrete time series. In addition to deterministic algorithms that learn the a posteriori most likely models and compute their posterior probabilities, we introduce a family of variable-dimension Markov chain Monte Carlo samplers, facilitating further exploration of the posterior. The performance of the proposed methods in model selection, Markov order estimation and prediction is illustrated through simulation experiments and real-world applications.
Publication Date
2021
Online Publication Date
Acceptance Date
Keywords
49 Mathematical Sciences, 46 Information and Computing Sciences, 4905 Statistics, 4611 Machine Learning, 2.5 Research design and methodologies (aetiology), 2 Aetiology
Journal Title
IEEE International Symposium on Information Theory - Proceedings
Journal ISSN
2157-8095
Volume Title
2021-July
Publisher
IEEE