AUEB Library - Digital Repository

PYXIDA Institutional Repository
and Digital Library

Username
Password

Collections :	Ιδρυματικό Αποθετήριο ΟΠΑ / AUEB Institutional Repository Σχολή Επιστημών και Τεχνολογίας της Πληροφορίας / School of Informatics Τμήμα Στατιστικής / Department of Statistics Μεταπτυχιακές Εργασίες / Postgraduate dissertations

Title :	Context tree weighting for signal processing, bayesian inference, and model selection: theoryand algorithms

Alternative Title :	Στάθμιση δέντρων συμφραζομένων για επεξεργασία σήματος, συμπερασματολογία κατά Bayes και επιλογή μοντέλου: θεωρία και αλγόριθμοι

Creator :	Skoularidou, Maria

Contributor :	Athens University of Economics and Business, Department of Statistics (Degree granting institution) Dellaportas, Petros (Επιβλέπων καθηγητής)

Type :	Text

Extent :	88 σ.

Language :	en

Abstract :	The goal of the present thesis is to explore, extend and utilize a family of algorithms that arose over the past twenty years in the Information Theoryliterature, under the umbrella of “Context Tree Weighting”. Although these methods were originally motivated by and applied to problems in source coding and data compression, we argue that there range of applicability extends to a large variety of problems in statistical inference and signal processing.We will examine the Maximum A Posteriori Probability Tree Algorithm(MAPT) as an efficient method for Bayesian inference, in the context of discrete series data. The MAPT algorithm computes the maximum a posteriori probability tree model, as well as the corresponding model posterior probability. Experimental results will be given, illustrating its performance,both on independent data and on more complex signals generated by variable memory Markov chains.

Abstract :

The goal of the present thesis is to explore, extend and utilize a family of algorithms that arose over the past twenty years in the Information Theoryliterature, under the umbrella of “Context Tree Weighting”. Although these methods were originally motivated by and applied to problems in source coding and data compression, we argue that there range of applicability extends to a large variety of problems in statistical inference and signal processing.We will examine the Maximum A Posteriori Probability Tree Algorithm(MAPT) as an efficient method for Bayesian inference, in the context of discrete series data. The MAPT algorithm computes the maximum a posteriori probability tree model, as well as the corresponding model posterior probability. Experimental results will be given, illustrating its performance,both on independent data and on more complex signals generated by variable memory Markov chains.

Subject :	Signal processing Bayesian model Mean marginal likelihood algorithms(CTW)

Date Issued :	23-11-2015

Licence :

File: Skoularidou_2015.pdf

Type: application/pdf

Login