Context Tree Switching

14 Nov 2011 · Joel Veness, Kee Siong Ng, Marcus Hutter, Michael Bowling ·

This paper describes the Context Tree Switching technique, a modification of Context Tree Weighting for the prediction of binary, stationary, n-Markov sources. By modifying Context Tree Weighting's recursive weighting scheme, it is possible to mix over a strictly larger class of models without increasing the asymptotic time or space complexity of the original algorithm. We prove that this generalization preserves the desirable theoretical properties of Context Tree Weighting on stationary n-Markov sources, and show empirically that this new technique leads to consistent improvements over Context Tree Weighting as measured on the Calgary Corpus.

PDF Abstract

Code

Add Remove Mark official

hardworkar/ctw

Datasets

Add Datasets introduced or used in this paper

Edit Social Preview

Context Tree Switching

Code Edit Add Remove Mark official

Categories

Datasets Edit

Code

Add Remove Mark official

Datasets